Develops methods to measure and reduce fairness in datasets with limited protected attribute labels.
problem Measuring and reducing fairness in datasets with limited protected attribute labels.
method Proposes methods to estimate fairness metrics and train models to limit fairness violations using probabilistic protected attribute labels.
result Our methods provide tighter bounds on true disparity and effectively reduce fairness violations with lesser fairness-accuracy trade-offs.
MASC balances dataset representation using affinity clustering and distribution discrepancies.
problem Representation bias in datasets due to group imbalance.
method MASC uses affinity clustering and pairwise distribution discrepancies to balance non-protected and protected groups.
result MASC effectively debiases target datasets, comparable to existing methods.
The paper proposes methods to infer from privacy-protected data using simulation-based techniques.
problem Valid statistical inference from privacy-protected data is computationally challenging.
method Simulation-based inference methods, including sequential Monte Carlo and neural conditional density estimators.
result Valid statistical inferences can be made from privacy-protected data.
ARL improves fairness without protected features, showing AUC improvements for worst-case groups.
problem Training fairness in ML without known protected features.
method Adversarially Reweighted Learning (ARL) using non-protected features and task labels.
result ARL improves Rawlsian Max-Min fairness with notable AUC improvements for worst-case groups.
PASS protects private attributes by stochastically substituting data.
problem Protecting private attributes in ML services while maintaining data utility.
method PASS uses stochastic data substitution with a novel loss function derived from information theory.
result PASS effectively protects private attributes across various datasets.
Publish a core-set of data to protect against adversarial use.
problem Protecting datasets from adversarial use.
method Construct a fair core-set for linear and neural models.
result Core-sets improve primary task performance while hindering unwanted tasks.
Framework for fair classification with noisy protected attributes and provable guarantees.
problem Fair classification with noisy protected attributes.
method Optimization framework for linear and linear-fractional fairness constraints, handling multiple non-binary attributes.
result Provably fair classifier with minimal accuracy loss, even with large noise.
Proposes a new method for fairness in machine learning with multiple protected attributes.
problem Ensuring fairness in machine learning models with continuous and multiple protected attributes.
method Distance covariance regularisation framework to mitigate association between model predictions and protected attributes.
result Demonstrates effectiveness in mitigating fairness gerrymandering in regression tasks.
Fair clustering under the disparate impact doctrine requires that population of each protected group should be approximately equal in every cluster. Previous work investigated a difficult-to-scale pre-processing step for k-center and k-median style algorithms for the special case of this problem when the number of …
We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group labels, either at training or runtime. To address this, we investigate improving fairness metrics for …
New algorithm mitigates bias in subset selection with noisy protected attributes.
problem Mitigating bias in subset selection when protected attributes are noisy.
method Formulated a denoised selection problem and developed a linear-programming based approximation algorithm.
result The approach can produce fairer subsets despite noisy protected attributes.
privGAN protects synthetic data from membership inference attacks.
problem Membership inference attacks on synthetic data generated by GANs.
method Developed a new GAN architecture (privGAN) that not only generates synthetic data but also defends against membership inference attacks.
result privGAN provides protection against membership inference attacks without significantly compromising downstream performance.
Interpretability and fairness are critical in computer vision and machine learning applications, in particular when dealing with human outcomes, e.g. inviting or not inviting for a job interview based on application materials that may include photographs. One promising direction to achieve fairness is by learning data …
Fair HAC algorithms ensure clustering fairness across protected groups.
problem Ensuring clustering fairness in HAC algorithms when datasets contain biases.
method Proposes fair algorithms for HAC that enforce fairness constraints regardless of distance linkage criteria.
result Our fair HAC algorithms find fairer clusterings compared to vanilla HAC and other fair clustering approaches.
Study removes bias from chest X-ray embeddings using orthogonalization.
problem Reduces bias in chest X-ray embeddings due to protected features.
method Orthogonalization technique to remove protected feature effects.
result Orthogonalization removes bias and makes predictions of protected attributes infeasible.
Study on protecting sensitive properties of datasets during analysis.
problem Ensuring privacy of sensitive properties in datasets.
method Proposes definitions and mechanisms for attribute privacy using the Pufferfish framework.
result Developed efficient and inefficient mechanisms for attribute privacy.
Large-scale datasets play a fundamental role in training deep learning models. However, dataset collection is difficult in domains that involve sensitive information. Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by th…
NTL protects AI models by restricting their generalization ability to specific domains.
problem Protecting AI models as intellectual property in a secure and robust manner.
method Non-Transferable Learning (NTL) captures exclusive data representation and restricts model generalization ability.
result NTL provides robust resistance to watermark removal and data-centric protection for usage authorization.
Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval. In this work, we consider the potential bias based on protected attributes (e.g., race and gender), and tackle this problem by learning …
Ward2ICU dataset protects patient privacy while generating synthetic ICU transitions data.
problem Protecting patient privacy while creating synthetic ICU transition data.
method Wasserstein Generative Adversarial Network (GAN) to generate synthetic data, class label balancing.
result Quality of synthetic data generation assessed through binary classification task.
Paper introduces LR to generate synthetic data with privacy protection.
problem Privacy concerns limit the use of sensitive datasets.
method Local Resampler (LR) using k-nearest neighbors algorithm.
result LR effectively mitigates outlier-driven disclosure risks.
Protects user privacy in models using optional personal data.
problem Ensuring fairness for users who opt-out of data sharing.
method Formalizes protection requirements, introduces Protected User Consent (PUC), devises data augmentation strategy.
result PUC-compliant models can improve performance without disadvantaging opt-out users.
As AI systems develop in complexity it is becoming increasingly hard to ensure non-discrimination on the basis of protected attributes such as gender, age, and race. Many recent methods have been developed for dealing with this issue as long as the protected attribute is explicitly available for the algorithm. We addre…
New method learns fair representations by separating out protected attributes.
problem Learning fair representations invariant to protected attributes.
method FD-VAE: disentangles latent space into target, protected, and mutual attributes.
result FD-VAE outperforms previous methods in fairness metrics.
The paper tackles fairness in estimating graphical models, especially for protected attributes.
problem Fairness issues in estimating graphical models, particularly for sensitive characteristics.
method Integrates pairwise graph disparity error and a tailored loss function into a multi-objective optimization problem.
result Successfully mitigates bias in graphical model estimation without compromising model performance.
Quantile regression is a tool for learning conditional distributions. In this paper we study quantile regression in the setting where a protected attribute is unavailable when fitting the model. This can lead to "unfair'' quantile estimators for which the effective quantiles are very different for the subpopulations de…
There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, or age. However, this raises two significant challenges: (1) protected attributes may not be available or it may not be legal to use…
This paper presents a method to generate synthetic data with differential privacy to protect user privacy while maintaining data trends.
problem Protecting user privacy while using real data for AI applications.
method Develops a practical guide to generating synthetic data using differential privacy.
result Synthetic data can be generated to preserve trends of real data while ensuring strong privacy protections.
LDA-XGB1 balances fairness and accuracy in lending models.
problem Fair lending practices and model interpretability in binary classification.
method Biobjective optimization using binning and information value, leveraging XGBoost.
result Achieves effective balance between accuracy, fairness, and interpretability.
New fairness criterion for risk-sensitive decisions in regulated industries.
problem Ensuring equitable outcomes in risk-sensitive decision-making.
method Marginal fairness for generalized distortion risk measures, two-step decision-making process.
result Ensures fairness in decision-making under risk measures, regardless of protected attributes.
In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap …
Additive noise protects privacy in releasing datasets for SVM classification.
problem Maintaining privacy in releasing datasets for SVM classification.
method Additive noise applied to obfuscate the dataset, optimizing privacy and utility measures.
result Optimal noise distribution ensures close classifier performance between original and obfuscated datasets, achieving local differential privacy.
New framework for fair classification in adversarial settings with provable guarantees.
problem Fairness in classification with adversarial perturbations of protected attributes.
method Optimization framework for learning fair classifiers with provable guarantees.
result Near-tightness of accuracy and fairness guarantees for multiple protected attributes and various hypothesis classes.
Deep chest X-ray classifiers show bias in predicting diagnoses.
problem Bias in deep learning classifiers predicting diagnoses from chest X-rays.
method Trained convolutional neural networks on multiple public datasets to predict 14 diagnostic labels.
result True positive rates vary significantly among different protected attributes, indicating bias.
CST detects discrimination by comparing protected and non-protected individuals with a counterfactual.
problem Detecting discrimination in classifiers using legal fairness conditions.
method Operationalizes fairness given the difference using counterfactual reasoning.
result CST uncovers more discrimination cases than traditional situation testing.
The study tests and optimizes fairness in credit scoring models.
problem Discrimination in credit scoring models based on protected attributes.
method Formal testing and variable identification to optimize fairness and performance.
result Guidance on monitoring and improving algorithmic fairness in credit scoring.
Intersectionality is a framework that analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including race, gender, sexual orientation, class, and disability. Intersectionality theory therefore implies it is important that fairness in artificial intelligence systems b…
Differential privacy for simple linear regression protects small datasets from individual data leaks.
problem Protecting sensitive personal information in small datasets from individual data leaks.
method Differential privacy algorithms for simple linear regression tailored for small datasets (tens to hundreds of datapoints).
result Robust estimators like Theil-Sen perform well on small datasets, but standard algorithms improve as dataset size increases.
Paper proposes protecting DNN models with secret key preprocessing.
problem Protecting deep learning models from unauthorized access.
method Block-wise pixel shuffling with secret key for preprocessing.
result Protected models maintain close performance to non-protected models with correct key, but accuracy drops significantly with incorrect key.
New mechanism protects neural network weights from privacy attacks during self-supervised learning.
problem Privacy risks during fine-tuning stage of self-supervised learning.
method Proposes a novel differential privacy mechanism using additive logistic noise.
result Reduces membership inference attack accuracy to 50% while maintaining below 5% performance loss.
New method steals deep neural network knowledge using unlabeled data.
problem Stealing knowledge from protected deep neural networks.
method Generating composite images to mimic mentor neural networks.
result Student network successfully mimics mentor network and steals knowledge.
Paper tackles fairness in CCA by minimizing correlation disparity error.
problem Fairness issues in CCA.
method Framework to minimize correlation disparity error in CCA.
result Reduces correlation disparity error without sacrificing CCA accuracy.
SEP uses checkpoints to protect data from training good models.
problem Protecting data from competitors training high-performance models.
method Forming perturbed examples using model checkpoints' gradients to ensure they are always unrecognized.
result SEP significantly reduces model accuracy when trained on perturbed data, demonstrating its effectiveness.
New attacks prevent both supervised and contrastive learning from private data.
problem Preventing unauthorized use of private data and commercial datasets.
method Contrastive-like data augmentations in supervised error minimization or maximization frameworks.
result Achieve state-of-the-art worst-case unlearnability across SL and CL algorithms.
For people with chronic pain, the assessment of protective behavior during physical functioning is essential to understand their subjective pain-related experiences (e.g., fear and anxiety toward pain and injury) and how they deal with such experiences (avoidance or reliance on specific body joints), with the ultimate …
Paper proposes a new approach to GDPR compliance using data protection analytics.
problem Lack of research on data protection risk management and difficulty in GDPR compliance.
method Quantitative approach to data protection risk-based compliance.
result Improves data protection impact assessments by integrating analytics and expert opinions.
Paper introduces SPADE method to protect classifiers from OOD and adversarial samples.
problem Protecting classifiers from out-of-distribution and adversarial samples.
method SPADE method based on GEV model in latent space.
result Provable protection against OOD and adversarial samples.
We consider the problem of obfuscating sensitive information while preserving utility, and we propose a machine learning approach inspired by the generative adversarial networks paradigm. The idea is to set up two nets: the generator, that tries to produce an optimal obfuscation mechanism to protect the data, and the c…