Fair Adversarial

Fair adversarial learning aims to create machine learning models that are both robust to adversarial attacks and unbiased with respect to sensitive attributes like race or gender. Current research focuses on developing algorithms and model architectures, such as adversarial variational autoencoders and fairness-aware adversarial training, that achieve this dual objective, often employing techniques like distributional robust optimization and class-wise calibration to mitigate disparities in model performance across different groups. This field is crucial for ensuring the ethical and equitable deployment of machine learning systems in various applications, from image recognition to job recommendations, by addressing the inherent trade-off between robustness and fairness.

Papers

October 30, 2024

FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training
Tejaswini Medi, Steffen Jung, Margret Keuper
Adversarial Attack Adversarial Training Adversarial Robustness Model Fairness Fair Adversarial

September 14, 2024

Detecting Looted Archaeological Sites from Satellite Image Time Series
Elliot Vincent, Mehraïl Saroufim, Jonathan Chemla, Yves Ubelmann, Philippe Marquis, Jean Ponce, Mathieu Aubry
Satellite Image Time Series Fair Adversarial Archaeological Artifact

June 9, 2024

Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning
Qi Qi, Quanqi Hu, Qihang Lin, Tianbao Yang
Neural Network Contrastive Learning Contrastive Loss Adversarial Loss Fair Adversarial Fair Contrastive

February 27, 2024

Towards Fairness-Aware Adversarial Learning
Yanghao Zhang, Tianle Zhang, Ronghui Mu, Xiaowei Huang, Wenjie Ruan
Adversarial Training Distributionally Robust Optimization Fair Adversarial Robust Fairness

January 23, 2024

DAFA: Distance-Aware Fair Adversarial Training
Hyungyu Lee, Saehyung Lee, Hyemi Jang, Junsung Park, Ho Bae, Sungroh Yoon
Adversarial Attack Adversarial Training Fair Adversarial Robust Fairness Adversarial Change

December 9, 2023

Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
Shiji Zhao, Ranjie Duan, Xizhe Wang, Xingxing Wei
Adversarial Training Adversarial Robustness Fair Adversarial Soft Label Distillation Adversarial Robustness Distillation

November 15, 2023

Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models
Yueqing Liang, Lu Cheng, Ali Payani, Kai Shu
Data Detection Backdoor Attack Abusive Language Detection Effective Model Fair Adversarial Robust Fairness Unveiling Vulnerability Abusive Language Classifier

October 27, 2023

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
Vincent Grari, Thibault Laugel, Tatsunori Hashimoto, Sylvain Lamprier, Marcin Detyniecki
Robust Optimization Algorithmic Fairness Fairness Notion Adversarial Debiasing Fair Adversarial Fairness Learning Local Fairness

March 25, 2023

CFA: Class-wise Calibrated Fair Adversarial Training
Zeming Wei, Yifei Wang, Yiwen Guo, Yisen Wang
Adversarial Example Adversarial Training Adversarial Robustness Adversarial Framework Adversarial Setting Fair Adversarial

September 20, 2022

Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation
Clara Rus, Jeffrey Luppes, Harrie Oosterhuis, Gido H. Schoenmacker
Algorithmic Bias Fair Representation Job Recommendation Adversarial Debiasing Fair Adversarial Fairness Aware Recommendation

September 19, 2022

Fairness in Face Presentation Attack Detection
Meiling Fang, Wufei Yang, Arjan Kuijper, Vitomir Struc, Naser Damer
Procedural Fairness Face Recognition Presentation Attack Detection Face Presentation Attack Detection Fairness Analysis Fair Adversarial

September 13, 2022

Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks
Hussain Hussain, Meng Cao, Sandipan Sikdar, Denis Helic, Elisabeth Lex, Markus Strohmaier, Roman Kern
Graph Neural Network Adversarial Attack Procedural Fairness Adversarial Agent Fair Adversarial

April 1, 2022

Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder
Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang
Variational Autoencoder Adversarial Learning Fair Representation Fair Representation Learning Fair Adversarial

March 16, 2022

Adversarial Learned Fair Representations using Dampening and Stacking
Max Knobbout
Adversarial Learning Fair Representation Fair Representation Learning Fair Decision Nondeterministic Stack Fair Adversarial