Study examines auditing fairness in evolving models, identifying strategic updates that preserve audit properties.
problem Auditing fairness in machine learning models that adapt to changing environments.
method Characterizes strategic updates that preserve audit properties, proposes a generic PAC auditing framework.
result Establishes distribution-free auditing bounds for statistical parity using the SP dimension.
Study efficient auditing of ML fairness models.
problem Scalability of auditing ML models for fairness.
method Query-based auditing algorithms for estimating demographic parity.
result Optimal deterministic and practical randomized algorithms for fairness estimation.
Peer-induced fairness framework audits algorithmic fairness in AI applications.
problem Current auditing methods lack robustness and fail to distinguish between algorithmic discrimination and subject limitations.
method Combines counterfactual fairness and peer comparison strategy for a reliable auditing tool.
result Demonstrates significant unfairness in micro-firms compared to non-micro firms, highlighting the framework's potential.
Fairness audits fail under missing protected labels, especially at zero access.
problem Understanding the reliability of fairness audits with incomplete protected-label data.
method Introduced a seed-calibrated stress test to separate missingness effects from seed-to-seed movement.
result Missing protected labels do not significantly alter fairness mitigation methods, but they can lead to harmful intersectional outcomes.
Study cost-effective fairness audits with partial feedback, improving over random exploration.
problem Auditing fairness of classifiers with limited true labels.
method Introduces cost model, proposes near-optimal algorithms for black-box and mixture models.
result Significantly lower audit costs compared to natural baselines.
Efficiently audits model fairness with continuous monitoring and flexible data collection.
problem Continuous monitoring and flexible data collection for fairness auditing.
method Sequential, anytime-valid inference and game-theoretic statistics.
result Demonstrated efficacy on three fairness datasets.
Auditing fairness of decision-makers is now in high demand. To respond to this social demand, several fairness auditing tools have been developed. The focus of this study is to raise an awareness of the risk of malicious decision-makers who fake fairness by abusing the auditing tools and thereby deceiving the social co…
Proposes auditing for envy-freeness in recommender systems to assess individual preferences.
problem Auditing fairness in recommender systems for individual preferences.
method Formulates a pure exploration problem in multi-armed bandits, proposing a sample-efficient algorithm with theoretical guarantees.
result Algorithm ensures fairness without deteriorating user experience on real-world datasets.
The paper addresses fairness in online learning by extending auditing schemes and presenting efficient algorithms.
problem Ensuring fairness in online learning while maximizing predictive accuracy.
method Extending auditing schemes to handle multiple auditors and presenting oracle-efficient algorithms.
result Presented algorithms achieve upper bounds on regret and fairness violations, improving on existing bounds.
Develops Active Fourier Auditor to estimate ML model properties without reconstructing them.
problem Verifying and auditing properties of Machine Learning models in real-world applications.
method A new framework that quantifies ML model properties using Fourier coefficients, without reconstructing the model.
result Active Fourier Auditor (AFA) is more accurate and sample-efficient than baselines for estimating robustness, individual fairness, and group fairness.
Study reveals AI skin cancer classifiers underperform for darker skin phototypes, advocating for fairness auditing.
problem AI bias in dermatology, particularly for darker skin phototypes.
method Predictive Representativity (PR) framework, evaluating classifiers on HAM10000 and BOSQUE Test sets.
result Substantial performance disparities by skin phototype, highlighting AI bias.
The paper shows how to audit fairness in decisions with hidden risk factors.
problem Estimating fairness in decisions influenced by hidden, unobservable risk factors.
method Derives unbiased estimates of risk using historical data and audits existing decision-making systems.
result One can compute meaningful bounds on treatment rates for high-risk individuals, even with hidden confounders.
Framework tests group fairness in machine learning models.
problem Detecting biases in machine learning classifiers.
method Optimal transport projections to audit group fairness.
result Statistical test for various fairness notions efficiently computed.
EL framework certifies and flags bias in ML models without distributional assumptions.
problem Systematic performance disparities across sensitive subpopulations in ML models.
method Empirical likelihood-based approach for non-parametric fairness auditing.
result EL framework outperforms bootstrap methods in certification and subpopulation discovery.
Machine learning algorithms are extensively used to make increasingly more consequential decisions about people, so achieving optimal predictive performance can no longer be the only focus. A particularly important consideration is fairness with respect to race, gender, or any other sensitive attribute. This paper stud…
Investigates fairness in pipeline models where individuals may drop out.
problem Fairness in pipeline models where individuals may drop out and subsequent stages depend on remaining individuals.
method Rigorous framework for evaluating fairness guarantees, showing that naïve auditing is insufficient and dependence must exist between stages.
result Fairness in pipelines can be arbitrary, even with just two stages, and requires dependence between stages.
New methods target conditional demographic parity using optimal transport distances.
problem Auditing and enforcing conditional demographic parity (CDP) in models with complex conditioning variables.
method Developed novel measures of conditional demographic disparity (CDD) based on optimal transport distances and regularization-based approaches.
result Validated methods airbit{} and airlp{} effectively target CDP in real-world datasets with continuous model outputs.
Neural networks help auditors efficiently assess financial statements by learning underlying data patterns.
problem Efficiently auditing large volumes of financial statements and journal entries.
method Vector Quantised-Variational Autoencoder (VQ-VAE) neural networks.
result VQ-VAE neural networks can learn a quantized representation of accounting data, uncovering latent factors and providing a representative audit sample.
Synthetic data mimics real-world demographics for fairness testing.
problem Lack of complete, representative datasets for fairness testing.
method Construct synthetic datasets using overlapping real and separate datasets.
result Synthetic data yields consistent fairness metrics with real data.
FairTrade uses variational inference to create fair predictions in causal models.
problem Creating fair predictions in machine learning models with causal reasoning.
method FairTrade uses variational inference to account for unobserved confounders and integrates fairness constraints on causal paths.
result Demonstrates the effectiveness of FairTrade in creating fair predictions in both simulated and real-world datasets.
Procedure for determining less discriminatory alternatives in AI audits with limited resources.
problem Difficulty in proving less discriminatory alternatives in AI audits due to resource constraints.
method Closed-form upper bound for loss-fairness Pareto frontier, enabling claimants to fit PFs without training large models.
result A scaling law for loss-fairness Pareto frontiers, allowing claimants to determine if an LDA exists with limited resources.
Algorithmic fairness is a field of study that addresses the systematic disadvantage of marginalized groups in machine learning systems.
problem Modern machine learning systems increasingly determine access to economic and social opportunities, leading to structural inequalities and prejudices.
method Statistical and structural approaches to algorithmic fairness.
result The field of algorithmic fairness emerged to address the systematic disadvantage of marginalized groups in machine learning systems.
Many existing fairness criteria for machine learning involve equalizing some metric across protected groups such as race or gender. However, practitioners trying to audit or enforce such group-based criteria can easily face the problem of noisy or biased protected group information. First, we study the consequences of …
We extend the fair machine learning literature by considering the problem of proportional centroid clustering in a metric context. For clustering n points with k centers, we define fairness as proportionality to mean that any n/k points are entitled to form their own cluster if there is another center that is clo…
Efficiently approximates fairness-accuracy trade-offs for diverse datasets.
problem Inherent trade-off between fairness and accuracy in machine learning models.
method You-Only-Train-Once (YOTO) framework for computationally efficient approximation.
result Robust methodology for auditing model fairness with statistical guarantees.
Framework for assessing fairness across similar predictive models.
problem Fairness in predictive models across different groups.
method Develops a framework for characterizing fairness over the set of good models under selective labels.
result Framework can replace or audit models for better fairness properties.
Survey of technologies for trustworthy machine learning systems.
problem Building machine learning systems that are fair, explainable, auditable, and secure.
method Survey of technologies across data and model stages of machine learning.
result Four categories of system properties (fairness, explainability, auditability, safety & security) are essential for trustworthy systems.
Mathematical model audits social media algorithms to prevent bias.
problem Algorithmic filtering can bias users' decisions and societal norms.
method Formalized mathematical framework for auditing social media algorithms.
result Data-driven statistical auditing procedure to regulate algorithmic bias.
Machine learning algorithms are now frequently used in sensitive contexts that substantially affect the course of human lives, such as credit lending or criminal justice. This is driven by the idea that `objective' machines base their decisions solely on facts and remain unaffected by human cognitive biases, discrimina…
A new method uses LLMs to discover causal pathways that affect fairness in machine learning.
problem Discovering fairness-relevant causal pathways in the presence of noise and confounding.
method Hybrid LLM-guided causal discovery framework combining active learning and dynamic scoring.
result LLM-guided methods, including the proposed active, dynamically scored variant, outperform baselines in recovering fairness-relevant structure under noisy conditions.
Prediction systems are successfully deployed in applications ranging from disease diagnosis, to predicting credit worthiness, to image recognition. Even when the overall accuracy is high, these systems may exhibit systematic biases that harm specific subpopulations; such biases may arise inadvertently due to underrepre…
Model shows partial compliance can lead to less fair outcomes than expected.
problem How partial compliance affects fairness in competitive markets.
method Simple model of employment market, simulation to explore effects.
result Partial compliance can lead to less fair outcomes than expected.
Decomposes bias in linear models under demographic parity constraints.
problem Understanding and quantifying bias in linear models under fairness constraints.
method Post-processing framework to decompose bias into direct and indirect components.
result Analytical characterization of how demographic parity reshapes model coefficients.
As artificial intelligence plays an increasingly important role in our society, there are ethical and moral obligations for both businesses and researchers to ensure that their machine learning models are designed, deployed, and maintained responsibly. These models need to be rigorously audited for fairness, robustness…
Federated learning can propagate bias from a few parties to all participants.
problem Bias from a few parties in federated learning can spread to all participants.
method Analysis of naturally partitioned real-world datasets.
result Bias in federated learning is higher than in centralized training.
New methods detect unfairness in multiclass classifiers using DCP.
problem Detecting unfairness in multiclass classifiers.
method Generalizes DCP to multiclass, provides optimization methods.
result Detects classifiers treating a significant fraction of the population unfairly.
Personalized interventions in social services, education, and healthcare leverage individual-level causal effect predictions in order to give the best treatment to each individual or to prioritize program interventions for the individuals most likely to benefit. While the sensitivity of these domains compels us to eval…
Where machine-learned predictive risk scores inform high-stakes decisions, such as bail and sentencing in criminal justice, fairness has been a serious concern. Recent work has characterized the disparate impact that such risk scores can have when used for a binary classification task. This may not account, however, fo…
Signed compression progress on a sealed audit is goodhart-resistant.
problem Intrinsic motivation for agents to improve their world models by compressing experience.
method Rewarding agents for the signed decrease of a fixed sealed-audit loss.
result Cumulative reward telescopes exactly to endpoint audit improvement, preventing infinite reward push while true audit performance stagnates.
Big data transforms accounting and auditing, enhancing insights but posing challenges.
problem Challenges in data privacy and security with increased data sources.
method Utilizing AI and machine learning for efficient data analysis and anomaly detection.
result Enhanced analytics tools and continuous learning are key to overcoming challenges.
New method audits DP guarantees without noise or subsampling info.
problem Auditing DP guarantees of ML models without prior info.
method Histogram-based density estimation for lower bounds.
result Natural generalization of membership inference auditing.
This study improves audit sampling by using sequential procedures with statistical guarantees.
problem Improving audit efficiency and reliability with statistical methods.
method Formulated as a sequential testing problem, defining null and alternative hypotheses, stopping and decision rules, and exact boundary conditions.
result Exact design yields ex ante control of decision error probabilities, and simulation-based implementation approximates this design.
RESHAPE explains financial statement anomalies by aggregating explanations from AENNs.
problem Detecting and explaining accounting anomalies in financial audits is challenging.
method Proposes RESHAPE to explain model output on an aggregated attribute-level.
result RESHAPE provides more comprehensible explanations compared to existing methods.
AI-driven framework improves enterprise financial audits and risk identification.
problem Manual auditing is inefficient and limited by data complexity and evolving fraud tactics.
method Machine learning algorithms (SVM, RF, KNN) applied to a dataset of audit project counts, violations, and fraud instances.
result Random Forest achieves best performance with F1-score of 0.9012, identifying fraud and compliance anomalies.
New divergences help audit DP in high dimensions.
problem Challenges in auditing DP in high-dimensional data.
method Propose kernel Rényi divergence and its regularized version for auditing.
result Regularized kernel Rényi divergence can be estimated from samples in high dimensions.
Improved canary crafting for one-run privacy auditing reduces leakage estimates.
problem Detecting canaries in one-run privacy auditing to estimate leakage effectively.
method Optimizes canaries for detectability and diversity, using a greedy initialization and bilevel optimization.
result Achieves stronger leakage estimates at lower computational cost.
Fine-tuning LLMs on privacy-sensitive data introduces privacy risk, and synthetic data audits can quantify this risk.
problem Fine-tuning LLMs on privacy-sensitive data introduces privacy risk.
method Generate synthetic canaries via high-temperature sampling from LLMs.
result Synthetic canaries are high-influence outliers that ensure strong audits.
Audited Conformal Prediction improves conditional coverage in pretrained models under distribution shift.
problem Uncertainty quantification for pretrained models under unknown distribution shift
method Leverages a small labeled dataset to train an audit model for marginal coverage, integrates outputs into conformal prediction framework
result Significantly higher conditional coverage than existing approaches