🎯 Top Personalized Recommendations
UTEP
Why we think this paper is great for you:
This paper directly addresses fair and private machine learning, highlighting practical applications in critical domains. You will find its human-in-the-loop approach valuable for ensuring ethical AI systems.
This paper directly addresses fair and private machine learning, highlighting practical applications in critical domains. You will find its human-in-the-loop approach valuable for ensuring ethical AI systems.
Abstract
As machine learning systems move from theory to practice, they are increasingly tasked with decisions that affect healthcare access, financial opportunities, hiring, and public services. In these contexts, accuracy is only one piece of the puzzle - models must also be fair to different groups, protect individual privacy, and remain accountable to stakeholders. Achieving all three is difficult: differential privacy can unintentionally worsen disparities, fairness interventions often rely on sensitive data that privacy restricts, and automated pipelines ignore that fairness is ultimately a human and contextual judgment. We introduce FAIRPLAI (Fair and Private Learning with Active Human Influence), a practical framework that integrates human oversight into the design and deployment of machine learning systems. FAIRPLAI works in three ways: (1) it constructs privacy-fairness frontiers that make trade-offs between accuracy, privacy guarantees, and group outcomes transparent; (2) it enables interactive stakeholder input, allowing decision-makers to select fairness criteria and operating points that reflect their domain needs; and (3) it embeds a differentially private auditing loop, giving humans the ability to review explanations and edge cases without compromising individual data security. Applied to benchmark datasets, FAIRPLAI consistently preserves strong privacy protections while reducing fairness disparities relative to automated baselines. More importantly, it provides a straightforward, interpretable process for practitioners to manage competing demands of accuracy, privacy, and fairness in socially impactful applications. By embedding human judgment where it matters most, FAIRPLAI offers a pathway to machine learning systems that are effective, responsible, and trustworthy in practice. GitHub: https://github.com/Li1Davey/Fairplai
As machine learning systems move from theory to practice, they are increasingly tasked with decisions that affect healthcare access, financial opportunities, hiring, and public services. In these contexts, accuracy is only one piece of the puzzle - models must also be fair to different groups, protect individual privacy, and remain accountable to stakeholders. Achieving all three is difficult: differential privacy can unintentionally worsen disparities, fairness interventions often rely on sensitive data that privacy restricts, and automated pipelines ignore that fairness is ultimately a human and contextual judgment. We introduce FAIRPLAI (Fair and Private Learning with Active Human Influence), a practical framework that integrates human oversight into the design and deployment of machine learning systems. FAIRPLAI works in three ways: (1) it constructs privacy-fairness frontiers that make trade-offs between accuracy, privacy guarantees, and group outcomes transparent; (2) it enables interactive stakeholder input, allowing decision-makers to select fairness criteria and operating points that reflect their domain needs; and (3) it embeds a differentially private auditing loop, giving humans the ability to review explanations and edge cases without compromising individual data security. Applied to benchmark datasets, FAIRPLAI consistently preserves strong privacy protections while reducing fairness disparities relative to automated baselines. More importantly, it provides a straightforward, interpretable process for practitioners to manage competing demands of accuracy, privacy, and fairness in socially impactful applications. By embedding human judgment where it matters most, FAIRPLAI offers a pathway to machine learning systems that are effective, responsible, and trustworthy in practice. GitHub: https://github.com/Li1Davey/Fairplai
AI Summary
- FAIRPLAI addresses the "fairness–privacy–accuracy paradox" by explicitly integrating human judgment to navigate the inherent trade-offs, rather than seeking a purely automated solution. [2]
- The framework constructs "privacy–fairness frontiers" that visually represent the trade-offs between predictive accuracy, fairness disparities, and differential privacy budgets, enabling transparent decision-making. [2]
- FAIRPLAI introduces a "Human-in-the-Loop Interaction" module that formalizes stakeholder input through a `policy tuple` (F, ∆, ε, A, M, π), translating normative requirements into technical constraints and vice versa. [2]
- Empirical evaluations demonstrate that FAIRPLAI-selected models can consistently satisfy specified fairness and accuracy thresholds under strict privacy constraints in most datasets, outperforming automated baselines in reliable constraint adherence. [2]
- The bidirectional translation layer within FAIRPLAI exhibits high fidelity (86% upward, 91% downward), ensuring that stakeholder language is accurately mapped to technical specifications and vice versa, enhancing interpretability and trust. [2]
- Implementing joint fairness and privacy (Fair-Private ML) consistently incurs a cost in predictive accuracy compared to unconstrained baseline models, underscoring the need for explicit human-guided trade-off decisions. [2]
- Fairness–Privacy–Accuracy Paradox: The inherent tension where optimizing one objective (fairness, privacy, or accuracy) often undermines the others. [2]
- FAIRPLAI (Fair and Private Learning with Active Human Influence): A human-in-the-loop framework that integrates human oversight into ML system design and deployment to manage fairness, privacy, and accuracy trade-offs. [2]
- Privacy–Fairness Frontier: A structured representation, often visualized as curves or surfaces, showing the feasible trade-offs between accuracy, fairness disparities, and differential privacy budgets (ε) for a family of models. [2]
- Differential privacy's impact on fairness is context-dependent, sometimes reducing disparities for categorical attributes but showing mixed effects for binary ones, highlighting the necessity of human oversight for nuanced judgments. [1]
UIUC
Why we think this paper is great for you:
This paper directly investigates adversarial bias and data poisoning attacks on fairness, which is crucial for understanding vulnerabilities in AI systems. It offers insights into protecting against data manipulation that impacts fairness.
This paper directly investigates adversarial bias and data poisoning attacks on fairness, which is crucial for understanding vulnerabilities in AI systems. It offers insights into protecting against data manipulation that impacts fairness.
Abstract
With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. The majority of the work in algorithmic fairness focus on assessing and improving the fairness of machine learning systems. There is relatively little research on fairness vulnerability, i.e., how an AI system's fairness can be intentionally compromised. In this work, we first provide a theoretical analysis demonstrating that a simple adversarial poisoning strategy is sufficient to induce maximally unfair behavior in naive Bayes classifiers. Our key idea is to strategically inject a small fraction of carefully crafted adversarial data points into the training set, biasing the model's decision boundary to disproportionately affect a protected group while preserving generalizable performance. To illustrate the practical effectiveness of our method, we conduct experiments across several benchmark datasets and models. We find that our attack significantly outperforms existing methods in degrading fairness metrics across multiple models and datasets, often achieving substantially higher levels of unfairness with a comparable or only slightly worse impact on accuracy. Notably, our method proves effective on a wide range of models, in contrast to prior work, demonstrating a robust and potent approach to compromising the fairness of machine learning systems.
With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. The majority of the work in algorithmic fairness focus on assessing and improving the fairness of machine learning systems. There is relatively little research on fairness vulnerability, i.e., how an AI system's fairness can be intentionally compromised. In this work, we first provide a theoretical analysis demonstrating that a simple adversarial poisoning strategy is sufficient to induce maximally unfair behavior in naive Bayes classifiers. Our key idea is to strategically inject a small fraction of carefully crafted adversarial data points into the training set, biasing the model's decision boundary to disproportionately affect a protected group while preserving generalizable performance. To illustrate the practical effectiveness of our method, we conduct experiments across several benchmark datasets and models. We find that our attack significantly outperforms existing methods in degrading fairness metrics across multiple models and datasets, often achieving substantially higher levels of unfairness with a comparable or only slightly worse impact on accuracy. Notably, our method proves effective on a wide range of models, in contrast to prior work, demonstrating a robust and potent approach to compromising the fairness of machine learning systems.
NUDT
Why we think this paper is great for you:
You will find this highly relevant as it focuses on mitigating bias through fair clustering in unsupervised learning. It provides a scalable framework for ensuring fairness in large datasets.
You will find this highly relevant as it focuses on mitigating bias through fair clustering in unsupervised learning. It provides a scalable framework for ensuring fairness in large datasets.
Abstract
Fair clustering is crucial for mitigating bias in unsupervised learning, yet existing algorithms often suffer from quadratic or super-quadratic computational complexity, rendering them impractical for large-scale datasets. To bridge this gap, we introduce the Anchor-based Fair Clustering Framework (AFCF), a novel, general, and plug-and-play framework that empowers arbitrary fair clustering algorithms with linear-time scalability. Our approach first selects a small but representative set of anchors using a novel fair sampling strategy. Then, any off-the-shelf fair clustering algorithm can be applied to this small anchor set. The core of our framework lies in a novel anchor graph construction module, where we formulate an optimization problem to propagate labels while preserving fairness. This is achieved through a carefully designed group-label joint constraint, which we prove theoretically ensures that the fairness of the final clustering on the entire dataset matches that of the anchor clustering. We solve this optimization efficiently using an ADMM-based algorithm. Extensive experiments on multiple large-scale benchmarks demonstrate that AFCF drastically accelerates state-of-the-art methods, which reduces computational time by orders of magnitude while maintaining strong clustering performance and fairness guarantees.
Fair clustering is crucial for mitigating bias in unsupervised learning, yet existing algorithms often suffer from quadratic or super-quadratic computational complexity, rendering them impractical for large-scale datasets. To bridge this gap, we introduce the Anchor-based Fair Clustering Framework (AFCF), a novel, general, and plug-and-play framework that empowers arbitrary fair clustering algorithms with linear-time scalability. Our approach first selects a small but representative set of anchors using a novel fair sampling strategy. Then, any off-the-shelf fair clustering algorithm can be applied to this small anchor set. The core of our framework lies in a novel anchor graph construction module, where we formulate an optimization problem to propagate labels while preserving fairness. This is achieved through a carefully designed group-label joint constraint, which we prove theoretically ensures that the fairness of the final clustering on the entire dataset matches that of the anchor clustering. We solve this optimization efficiently using an ADMM-based algorithm. Extensive experiments on multiple large-scale benchmarks demonstrate that AFCF drastically accelerates state-of-the-art methods, which reduces computational time by orders of magnitude while maintaining strong clustering performance and fairness guarantees.
Duke University
Why we think this paper is great for you:
This paper delves into the ethical challenges of aligning AI with dynamic human moral preferences. It offers a critical perspective on the stability of feedback used in AI alignment.
This paper delves into the ethical challenges of aligning AI with dynamic human moral preferences. It offers a critical perspective on the stability of feedback used in AI alignment.
Abstract
Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of AI to dynamic human preferences should ideally account for "legitimate" changes to moral reasoning, while ignoring changes related to attention deficits, cognitive biases, or other arbitrary factors. However, common AI alignment approaches largely neglect temporal changes in preferences, posing serious challenges to proper alignment, especially in high-stakes applications of AI, e.g., in healthcare domains, where misalignment can jeopardize the trustworthiness of the system and yield serious individual and societal harms. This work investigates the extent to which people's moral preferences change over time, and the impact of such changes on AI alignment. Our study is grounded in the kidney allocation domain, where we elicit responses to pairwise comparisons of hypothetical kidney transplant patients from over 400 participants across 3-5 sessions. We find that, on average, participants change their response to the same scenario presented at different times around 6-20% of the time (exhibiting "response instability"). Additionally, we observe significant shifts in several participants' retrofitted decision-making models over time (capturing "model instability"). The predictive performance of simple AI models decreases as a function of both response and model instability. Moreover, predictive performance diminishes over time, highlighting the importance of accounting for temporal changes in preferences during training. These findings raise fundamental normative and technical challenges relevant to AI alignment, highlighting the need to better understand the object of alignment (what to align to) when user preferences change significantly over time.
Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of AI to dynamic human preferences should ideally account for "legitimate" changes to moral reasoning, while ignoring changes related to attention deficits, cognitive biases, or other arbitrary factors. However, common AI alignment approaches largely neglect temporal changes in preferences, posing serious challenges to proper alignment, especially in high-stakes applications of AI, e.g., in healthcare domains, where misalignment can jeopardize the trustworthiness of the system and yield serious individual and societal harms. This work investigates the extent to which people's moral preferences change over time, and the impact of such changes on AI alignment. Our study is grounded in the kidney allocation domain, where we elicit responses to pairwise comparisons of hypothetical kidney transplant patients from over 400 participants across 3-5 sessions. We find that, on average, participants change their response to the same scenario presented at different times around 6-20% of the time (exhibiting "response instability"). Additionally, we observe significant shifts in several participants' retrofitted decision-making models over time (capturing "model instability"). The predictive performance of simple AI models decreases as a function of both response and model instability. Moreover, predictive performance diminishes over time, highlighting the importance of accounting for temporal changes in preferences during training. These findings raise fundamental normative and technical challenges relevant to AI alignment, highlighting the need to better understand the object of alignment (what to align to) when user preferences change significantly over time.
Why we think this paper is great for you:
This paper explores the critical topic of data consent and respecting data owners' wishes in AI training datasets. It provides valuable insights into ethical data collection practices for AI systems.
This paper explores the critical topic of data consent and respecting data owners' wishes in AI training datasets. It provides valuable insights into ethical data collection practices for AI systems.
Abstract
The internet has become the main source of data to train modern text-to-image or vision-language models, yet it is increasingly unclear whether web-scale data collection practices for training AI systems adequately respect data owners' wishes. Ignoring the owner's indication of consent around data usage not only raises ethical concerns but also has recently been elevated into lawsuits around copyright infringement cases. In this work, we aim to reveal information about data owners' consent to AI scraping and training, and study how it's expressed in DataComp, a popular dataset of 12.8 billion text-image pairs. We examine both the sample-level information, including the copyright notice, watermarking, and metadata, and the web-domain-level information, such as a site's Terms of Service (ToS) and Robots Exclusion Protocol. We estimate at least 122M of samples exhibit some indication of copyright notice in CommonPool, and find that 60\% of the samples in the top 50 domains come from websites with ToS that prohibit scraping. Furthermore, we estimate 9-13\% with 95\% confidence interval of samples from CommonPool to contain watermarks, where existing watermark detection methods fail to capture them in high fidelity. Our holistic methods and findings show that data owners rely on various channels to convey data consent, of which current AI data collection pipelines do not entirely respect. These findings highlight the limitations of the current dataset curation/release practice and the need for a unified data consent framework taking AI purposes into consideration.
The internet has become the main source of data to train modern text-to-image or vision-language models, yet it is increasingly unclear whether web-scale data collection practices for training AI systems adequately respect data owners' wishes. Ignoring the owner's indication of consent around data usage not only raises ethical concerns but also has recently been elevated into lawsuits around copyright infringement cases. In this work, we aim to reveal information about data owners' consent to AI scraping and training, and study how it's expressed in DataComp, a popular dataset of 12.8 billion text-image pairs. We examine both the sample-level information, including the copyright notice, watermarking, and metadata, and the web-domain-level information, such as a site's Terms of Service (ToS) and Robots Exclusion Protocol. We estimate at least 122M of samples exhibit some indication of copyright notice in CommonPool, and find that 60\% of the samples in the top 50 domains come from websites with ToS that prohibit scraping. Furthermore, we estimate 9-13\% with 95\% confidence interval of samples from CommonPool to contain watermarks, where existing watermark detection methods fail to capture them in high fidelity. Our holistic methods and findings show that data owners rely on various channels to convey data consent, of which current AI data collection pipelines do not entirely respect. These findings highlight the limitations of the current dataset curation/release practice and the need for a unified data consent framework taking AI purposes into consideration.
University of Potsdam
Why we think this paper is great for you:
You will appreciate this paper's deep dive into the ethics of data within the sensitive domain of health. It examines how multimodal digital biomarkers expand the concept of health data.
You will appreciate this paper's deep dive into the ethics of data within the sensitive domain of health. It examines how multimodal digital biomarkers expand the concept of health data.
Abstract
Multimodal digital biomarkers (MDBs) integrate diverse physiological, behavioral, and contextual data to provide continuous representations of health. This paper argues that MDBs expand the concept of digital biomarkers along the dimensions of variability, complexity and abstraction, producing an ontological shift that datafies health and an epistemic shift that redefines health relevance. These transformations entail ethical implications for knowledge, responsibility, and governance in data-driven, preventive medicine.
Multimodal digital biomarkers (MDBs) integrate diverse physiological, behavioral, and contextual data to provide continuous representations of health. This paper argues that MDBs expand the concept of digital biomarkers along the dimensions of variability, complexity and abstraction, producing an ontological shift that datafies health and an epistemic shift that redefines health relevance. These transformations entail ethical implications for knowledge, responsibility, and governance in data-driven, preventive medicine.
Why we think this paper is great for you:
This paper discusses the ethical and legal implications of data collection for behavioral targeting. It provides insights into data protection regulations and the use of pseudonymous data.
This paper discusses the ethical and legal implications of data collection for behavioral targeting. It provides insights into data protection regulations and the use of pseudonymous data.
Abstract
Information about millions of people is collected for behavioural targeting, a type of marketing that involves tracking people's online behaviour for targeted advertising. It is hotly debated whether data protection law applies to behavioural targeting. Many behavioural targeting companies say that, as long as they do not tie names to data they hold about individuals, they do not process any personal data, and that, therefore, data protection law does not apply to them. European Data Protection Authorities, however, take the view that a company processes personal data if it uses data to single out a person, even if it cannot tie a name to these data. This paper argues that data protection law should indeed apply to behavioural targeting. Companies can often tie a name to nameless data about individuals. Furthermore, behavioural targeting relies on collecting information about individuals, singling out individuals, and targeting ads to individuals. Many privacy risks remain, regardless of whether companies tie a name to the information they hold about a person. A name is merely one of the identifiers that can be tied to data about a person, and it is not even the most practical identifier for behavioural targeting. Seeing data used to single out a person as personal data fits the rationale for data protection law: protecting fairness and privacy.
Information about millions of people is collected for behavioural targeting, a type of marketing that involves tracking people's online behaviour for targeted advertising. It is hotly debated whether data protection law applies to behavioural targeting. Many behavioural targeting companies say that, as long as they do not tie names to data they hold about individuals, they do not process any personal data, and that, therefore, data protection law does not apply to them. European Data Protection Authorities, however, take the view that a company processes personal data if it uses data to single out a person, even if it cannot tie a name to these data. This paper argues that data protection law should indeed apply to behavioural targeting. Companies can often tie a name to nameless data about individuals. Furthermore, behavioural targeting relies on collecting information about individuals, singling out individuals, and targeting ads to individuals. Many privacy risks remain, regardless of whether companies tie a name to the information they hold about a person. A name is merely one of the identifiers that can be tied to data about a person, and it is not even the most practical identifier for behavioural targeting. Seeing data used to single out a person as personal data fits the rationale for data protection law: protecting fairness and privacy.
Data Bias
MIT
Abstract
The cost of error in many high-stakes settings is asymmetric: misdiagnosing pneumonia when absent is an inconvenience, but failing to detect it when present can be life-threatening. Because of this, artificial intelligence (AI) models used to assist such decisions are frequently trained with asymmetric loss functions that incorporate human decision-makers' trade-offs between false positives and false negatives. In two focal applications, we show that this standard alignment practice can backfire. In both cases, it would be better to train the machine learning model with a loss function that ignores the human's objective and then adjust predictions ex post according to that objective. We rationalize this result using an economic model of incentive design with endogenous information acquisition. The key insight from our theoretical framework is that machine classifiers perform not one but two incentivized tasks: choosing how to classify and learning how to classify. We show that while the adjustments engineers use correctly incentivize choosing, they can simultaneously reduce the incentives to learn. Our formal treatment of the problem reveals that methods embraced for their intuitive appeal can in fact misalign human and machine objectives in predictable ways.
The cost of error in many high-stakes settings is asymmetric: misdiagnosing pneumonia when absent is an inconvenience, but failing to detect it when present can be life-threatening. Because of this, artificial intelligence (AI) models used to assist such decisions are frequently trained with asymmetric loss functions that incorporate human decision-makers' trade-offs between false positives and false negatives. In two focal applications, we show that this standard alignment practice can backfire. In both cases, it would be better to train the machine learning model with a loss function that ignores the human's objective and then adjust predictions ex post according to that objective. We rationalize this result using an economic model of incentive design with endogenous information acquisition. The key insight from our theoretical framework is that machine classifiers perform not one but two incentivized tasks: choosing how to classify and learning how to classify. We show that while the adjustments engineers use correctly incentivize choosing, they can simultaneously reduce the incentives to learn. Our formal treatment of the problem reveals that methods embraced for their intuitive appeal can in fact misalign human and machine objectives in predictable ways.
AI Ethics
YUX Design
Abstract
Frontier LLMs are optimised around high-resource assumptions about language, knowledge, devices, and connectivity. Whilst widely accessible, they often misfit conditions in the Global South. As a result, users must often perform additional work to make these systems usable. We term this alignment debt: the user-side burden that arises when AI systems fail to align with cultural, linguistic, infrastructural, or epistemic contexts. We develop and validate a four-part taxonomy of alignment debt through a survey of 411 AI users in Kenya and Nigeria. Among respondents measurable on this taxonomy (n = 385), prevalence is: Cultural and Linguistic (51.9%), Infrastructural (43.1%), Epistemic (33.8%), and Interaction (14.0%). Country comparisons show a divergence in Infrastructural and Interaction debt, challenging one-size-fits-Africa assumptions. Alignment debt is associated with compensatory labour, but responses vary by debt type: users facing Epistemic challenges verify outputs at significantly higher rates (91.5% vs. 80.8%; p = 0.037), and verification intensity correlates with cumulative debt burden (Spearmans rho = 0.147, p = 0.004). In contrast, Infrastructural and Interaction debts show weak or null associations with verification, indicating that some forms of misalignment cannot be resolved through verification alone. These findings show that fairness must be judged not only by model metrics but also by the burden imposed on users at the margins, compelling context-aware safeguards that alleviate alignment debt in Global South settings. The alignment debt framework provides an empirically grounded way to measure user burden, informing both design practice and emerging African AI governance efforts.
Frontier LLMs are optimised around high-resource assumptions about language, knowledge, devices, and connectivity. Whilst widely accessible, they often misfit conditions in the Global South. As a result, users must often perform additional work to make these systems usable. We term this alignment debt: the user-side burden that arises when AI systems fail to align with cultural, linguistic, infrastructural, or epistemic contexts. We develop and validate a four-part taxonomy of alignment debt through a survey of 411 AI users in Kenya and Nigeria. Among respondents measurable on this taxonomy (n = 385), prevalence is: Cultural and Linguistic (51.9%), Infrastructural (43.1%), Epistemic (33.8%), and Interaction (14.0%). Country comparisons show a divergence in Infrastructural and Interaction debt, challenging one-size-fits-Africa assumptions. Alignment debt is associated with compensatory labour, but responses vary by debt type: users facing Epistemic challenges verify outputs at significantly higher rates (91.5% vs. 80.8%; p = 0.037), and verification intensity correlates with cumulative debt burden (Spearmans rho = 0.147, p = 0.004). In contrast, Infrastructural and Interaction debts show weak or null associations with verification, indicating that some forms of misalignment cannot be resolved through verification alone. These findings show that fairness must be judged not only by model metrics but also by the burden imposed on users at the margins, compelling context-aware safeguards that alleviate alignment debt in Global South settings. The alignment debt framework provides an empirically grounded way to measure user burden, informing both design practice and emerging African AI governance efforts.
Data Representation
Presidency University
Abstract
An AI-powered data visualization platform that automates the entire data analysis process, from uploading a dataset to generating an interactive visualization. Advanced machine learning algorithms are employed to clean and preprocess the data, analyse its features, and automatically select appropriate visualizations. The system establishes the process of automating AI-based analysis and visualization from the context of data-driven environments, and eliminates the challenge of time-consuming manual data analysis. The combination of a Python Flask backend to access the dataset, paired with a React frontend, provides a robust platform that automatically interacts with Firebase Cloud Storage for numerous data processing and data analysis solutions and real-time sources. Key contributions include automatic and intelligent data cleaning, with imputation for missing values, and detection of outliers, via analysis of the data set. AI solutions to intelligently select features, using four different algorithms, and intelligent title generation and visualization are determined by the attributes of the dataset. These contributions were evaluated using two separate datasets to assess the platform's performance. In the process evaluation, the initial analysis was performed in real-time on datasets as large as 100000 rows, while the cloud-based demand platform scales to meet requests from multiple users and processes them simultaneously. In conclusion, the cloud-based data visualization application allowed for a significant reduction of manual inputs to the data analysis process while maintaining a high quality, impactful visual outputs, and user experiences
An AI-powered data visualization platform that automates the entire data analysis process, from uploading a dataset to generating an interactive visualization. Advanced machine learning algorithms are employed to clean and preprocess the data, analyse its features, and automatically select appropriate visualizations. The system establishes the process of automating AI-based analysis and visualization from the context of data-driven environments, and eliminates the challenge of time-consuming manual data analysis. The combination of a Python Flask backend to access the dataset, paired with a React frontend, provides a robust platform that automatically interacts with Firebase Cloud Storage for numerous data processing and data analysis solutions and real-time sources. Key contributions include automatic and intelligent data cleaning, with imputation for missing values, and detection of outliers, via analysis of the data set. AI solutions to intelligently select features, using four different algorithms, and intelligent title generation and visualization are determined by the attributes of the dataset. These contributions were evaluated using two separate datasets to assess the platform's performance. In the process evaluation, the initial analysis was performed in real-time on datasets as large as 100000 rows, while the cloud-based demand platform scales to meet requests from multiple users and processes them simultaneously. In conclusion, the cloud-based data visualization application allowed for a significant reduction of manual inputs to the data analysis process while maintaining a high quality, impactful visual outputs, and user experiences
Abstract
Enterprise relational databases increasingly contain vast amounts of non-semantic data - IP addresses, product identifiers, encoded keys, and timestamps - that challenge traditional semantic analysis. This paper introduces a novel Character-Level Autoencoder (CAE) approach that automatically identifies and groups semantically identical columns in non-semantic relational datasets by detecting column similarities based on data patterns and structures. Unlike conventional Natural Language Processing (NLP) models that struggle with limitations in semantic interpretability and out-of-vocabulary tokens, our approach operates at the character level with fixed dictionary constraints, enabling scalable processing of large-scale data lakes and warehouses. The CAE architecture encodes text representations of non-semantic relational table columns and extracts high-dimensional feature embeddings for data grouping. By maintaining a fixed dictionary size, our method significantly reduces both memory requirements and training time, enabling efficient processing of large-scale industrial data environments. Experimental evaluation demonstrates substantial performance gains: our CAE approach achieved 80.95% accuracy in top 5 column matching tasks across relational datasets, substantially outperforming traditional NLP approaches such as Bag of Words (47.62%). These results demonstrate its effectiveness for identifying and clustering identical columns in relational datasets. This work bridges the gap between theoretical advances in character-level neural architectures and practical enterprise data management challenges, providing an automated solution for schema understanding and data profiling of non-semantic industrial datasets at scale.
Enterprise relational databases increasingly contain vast amounts of non-semantic data - IP addresses, product identifiers, encoded keys, and timestamps - that challenge traditional semantic analysis. This paper introduces a novel Character-Level Autoencoder (CAE) approach that automatically identifies and groups semantically identical columns in non-semantic relational datasets by detecting column similarities based on data patterns and structures. Unlike conventional Natural Language Processing (NLP) models that struggle with limitations in semantic interpretability and out-of-vocabulary tokens, our approach operates at the character level with fixed dictionary constraints, enabling scalable processing of large-scale data lakes and warehouses. The CAE architecture encodes text representations of non-semantic relational table columns and extracts high-dimensional feature embeddings for data grouping. By maintaining a fixed dictionary size, our method significantly reduces both memory requirements and training time, enabling efficient processing of large-scale industrial data environments. Experimental evaluation demonstrates substantial performance gains: our CAE approach achieved 80.95% accuracy in top 5 column matching tasks across relational datasets, substantially outperforming traditional NLP approaches such as Bag of Words (47.62%). These results demonstrate its effectiveness for identifying and clustering identical columns in relational datasets. This work bridges the gap between theoretical advances in character-level neural architectures and practical enterprise data management challenges, providing an automated solution for schema understanding and data profiling of non-semantic industrial datasets at scale.
AI Transparency
Hochschule Mnchen
Abstract
This work will elaborate the fundamental principles of physical artificial intelligence (Physical AI) from a scientific and systemic perspective. The aim is to create a theoretical foundation that describes the physical embodiment, sensory perception, ability to act, learning processes, and context sensitivity of intelligent systems within a coherent framework. While classical AI approaches rely on symbolic processing and data driven models, Physical AI understands intelligence as an emergent phenomenon of real interaction between body, environment, and experience. The six fundamentals presented here are embodiment, sensory perception, motor action, learning, autonomy, and context sensitivity, and form the conceptual basis for designing and evaluating physically intelligent systems. Theoretically, it is shown that these six principles do not represent loose functional modules but rather act as a closed control loop in which energy, information, control, and context are in constant interaction. This circular interaction enables a system to generate meaning not from databases, but from physical experience, a paradigm shift that understands intelligence as an physical embodied process. Physical AI understands learning not as parameter adjustment, but as a change in the structural coupling between agents and the environment. To illustrate this, the theoretical model is explained using a practical scenario: An adaptive assistant robot supports patients in a rehabilitation clinic. This example illustrates that physical intelligence does not arise from abstract calculation, but from immediate, embodied experience. It shows how the six fundamentals interact in a real system: embodiment as a prerequisite, perception as input, movement as expression, learning as adaptation, autonomy as regulation, and context as orientation.
This work will elaborate the fundamental principles of physical artificial intelligence (Physical AI) from a scientific and systemic perspective. The aim is to create a theoretical foundation that describes the physical embodiment, sensory perception, ability to act, learning processes, and context sensitivity of intelligent systems within a coherent framework. While classical AI approaches rely on symbolic processing and data driven models, Physical AI understands intelligence as an emergent phenomenon of real interaction between body, environment, and experience. The six fundamentals presented here are embodiment, sensory perception, motor action, learning, autonomy, and context sensitivity, and form the conceptual basis for designing and evaluating physically intelligent systems. Theoretically, it is shown that these six principles do not represent loose functional modules but rather act as a closed control loop in which energy, information, control, and context are in constant interaction. This circular interaction enables a system to generate meaning not from databases, but from physical experience, a paradigm shift that understands intelligence as an physical embodied process. Physical AI understands learning not as parameter adjustment, but as a change in the structural coupling between agents and the environment. To illustrate this, the theoretical model is explained using a practical scenario: An adaptive assistant robot supports patients in a rehabilitation clinic. This example illustrates that physical intelligence does not arise from abstract calculation, but from immediate, embodied experience. It shows how the six fundamentals interact in a real system: embodiment as a prerequisite, perception as input, movement as expression, learning as adaptation, autonomy as regulation, and context as orientation.
Abstract
This third international workshop on explainable AI for the Arts (XAIxArts) brought together a community of researchers in HCI, Interaction Design, AI, explainable AI (XAI), and digital arts to explore the role of XAI for the Arts. Workshop held at the 17th ACM Conference on Creativity and Cognition (C&C 2025), online.
This third international workshop on explainable AI for the Arts (XAIxArts) brought together a community of researchers in HCI, Interaction Design, AI, explainable AI (XAI), and digital arts to explore the role of XAI for the Arts. Workshop held at the 17th ACM Conference on Creativity and Cognition (C&C 2025), online.
Data Transparency
Abstract
Dataset distillation (DD) compresses large datasets into smaller ones while preserving the performance of models trained on them. Although DD is often assumed to enhance data privacy by aggregating over individual examples, recent studies reveal that standard DD can still leak sensitive information from the original dataset due to the lack of formal privacy guarantees. Existing differentially private (DP)-DD methods attempt to mitigate this risk by injecting noise into the distillation process. However, they often fail to fully leverage the original dataset, resulting in degraded realism and utility. This paper introduces \libn, a novel framework that addresses the key limitations of current DP-DD by leveraging DP-generated data. Specifically, \lib initializes the distilled dataset with DP-generated data to enhance realism. Then, generated data refines the DP-feature matching technique to distill the original dataset under a small privacy budget, and trains an expert model to align the distilled examples with their class distribution. Furthermore, we design a privacy budget allocation strategy to determine budget consumption across DP components and provide a theoretical analysis of the overall privacy guarantees. Extensive experiments show that \lib significantly outperforms state-of-the-art DP-DD methods in terms of both dataset utility and robustness against membership inference attacks, establishing a new paradigm for privacy-preserving dataset distillation.
Dataset distillation (DD) compresses large datasets into smaller ones while preserving the performance of models trained on them. Although DD is often assumed to enhance data privacy by aggregating over individual examples, recent studies reveal that standard DD can still leak sensitive information from the original dataset due to the lack of formal privacy guarantees. Existing differentially private (DP)-DD methods attempt to mitigate this risk by injecting noise into the distillation process. However, they often fail to fully leverage the original dataset, resulting in degraded realism and utility. This paper introduces \libn, a novel framework that addresses the key limitations of current DP-DD by leveraging DP-generated data. Specifically, \lib initializes the distilled dataset with DP-generated data to enhance realism. Then, generated data refines the DP-feature matching technique to distill the original dataset under a small privacy budget, and trains an expert model to align the distilled examples with their class distribution. Furthermore, we design a privacy budget allocation strategy to determine budget consumption across DP components and provide a theoretical analysis of the overall privacy guarantees. Extensive experiments show that \lib significantly outperforms state-of-the-art DP-DD methods in terms of both dataset utility and robustness against membership inference attacks, establishing a new paradigm for privacy-preserving dataset distillation.
AI Bias
Kamiwaza AI
Abstract
Enterprise adoption of agentic AI systems requires reliable evaluation methods that reflect real-world deployment scenarios. Traditional LLM benchmarks suffer from training data contamination and fail to measure agentic capabilities such as multi-step tool use and decision-making under uncertainty. We present the Kamiwaza Agentic Merit Index (KAMI) v0.1, an enterprise-focused benchmark that addresses both contamination resistance and agentic evaluation. Through 170,000 LLM test items processing over 5.5 billion tokens across 35 model configurations, we demonstrate that traditional benchmark rankings poorly predict practical agentic performance. Notably, newer generation models like Llama 4 or Qwen 3 do not always outperform their older generation variants on enterprise-relevant tasks, contradicting traditional benchmark trends. We also present insights on cost-performance tradeoffs, model-specific behavioral patterns, and the impact of reasoning capabilities on token efficiency -- findings critical for enterprises making deployment decisions.
Enterprise adoption of agentic AI systems requires reliable evaluation methods that reflect real-world deployment scenarios. Traditional LLM benchmarks suffer from training data contamination and fail to measure agentic capabilities such as multi-step tool use and decision-making under uncertainty. We present the Kamiwaza Agentic Merit Index (KAMI) v0.1, an enterprise-focused benchmark that addresses both contamination resistance and agentic evaluation. Through 170,000 LLM test items processing over 5.5 billion tokens across 35 model configurations, we demonstrate that traditional benchmark rankings poorly predict practical agentic performance. Notably, newer generation models like Llama 4 or Qwen 3 do not always outperform their older generation variants on enterprise-relevant tasks, contradicting traditional benchmark trends. We also present insights on cost-performance tradeoffs, model-specific behavioral patterns, and the impact of reasoning capabilities on token efficiency -- findings critical for enterprises making deployment decisions.
KIT
Abstract
Collaboration with artificial intelligence (AI) has improved human decision-making across various domains by leveraging the complementary capabilities of humans and AI. Yet, humans systematically overrely on AI advice, even when their independent judgment would yield superior outcomes, fundamentally undermining the potential of human-AI complementarity. Building on prior work, we identify prevailing incentive structures in human-AI decision-making as a structural driver of this overreliance. To address this misalignment, we propose an alternative incentive mechanism designed to counteract systemic overreliance. We empirically evaluate this approach through a behavioral experiment with 180 participants, finding that the proposed mechanism significantly reduces overreliance. We also show that while appropriately designed incentives can enhance collaboration and decision quality, poorly designed incentives may distort behavior, introduce unintended consequences, and ultimately degrade performance. These findings underscore the importance of aligning incentives with task context and human-AI complementarities, and suggest that effective collaboration requires a shift toward context-sensitive incentive design.
Collaboration with artificial intelligence (AI) has improved human decision-making across various domains by leveraging the complementary capabilities of humans and AI. Yet, humans systematically overrely on AI advice, even when their independent judgment would yield superior outcomes, fundamentally undermining the potential of human-AI complementarity. Building on prior work, we identify prevailing incentive structures in human-AI decision-making as a structural driver of this overreliance. To address this misalignment, we propose an alternative incentive mechanism designed to counteract systemic overreliance. We empirically evaluate this approach through a behavioral experiment with 180 participants, finding that the proposed mechanism significantly reduces overreliance. We also show that while appropriately designed incentives can enhance collaboration and decision quality, poorly designed incentives may distort behavior, introduce unintended consequences, and ultimately degrade performance. These findings underscore the importance of aligning incentives with task context and human-AI complementarities, and suggest that effective collaboration requires a shift toward context-sensitive incentive design.
Help us improve your experience!
This project is on its early stages your feedback can be pivotal on the future of the project.
Let us know what you think about this week's papers and suggestions!
Give Feedback