Fairness Attack

Fairness attacks target machine learning models, particularly those designed to be fair, aiming to expose or exacerbate biases within them. Current research focuses on developing methods to manipulate model inputs or training data (e.g., through node injection in graph neural networks or poisoning attacks on diffusion models) to deceptively undermine fairness metrics while maintaining model utility. This research highlights the vulnerability of fairness-aware algorithms and underscores the need for robust methods to detect and mitigate such attacks, thereby improving the trustworthiness and reliability of AI systems in sensitive applications.

Papers

October 23, 2024

BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
Jiaqi Xue, Qian Lou, Mengxin Zheng
Native Robustness Fairness Method Fairness Attack

October 9, 2024

PFAttack: Stealthy Attack Bypassing Group Fairness in Federated Learning
Jiashi Gao, Ziwei Wang, Xiangyu Zhao, Xin Yao, Xuetao Wei
Group Fairness Byzantine Robust Aggregation Fairness Attack

June 5, 2024

Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
Zihan Luo, Hong Huang, Yongkang Zhou, Jiping Zhang, Nuo Chen, Hai Jin
Graph Neural Network Full Model Node Injection Fair GNN Fairness Attack

February 28, 2024

Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective
Xinjian Luo, Yangfan Jiang, Fei Wei, Yuncheng Wu, Xiaokui Xiao, Beng Chin Ooi
Diffusion Model Privacy Preserving Pre Trained Diffusion Model Adversarial Perspective Fair Credit Privacy Level Property Inference Attack Fairness Attack Collaborative Diffusion Model

December 16, 2023

TrojFair: Trojan Fairness Attacks
Mengxin Zheng, Jiaqi Xue, Yi Sheng, Lei Yang, Qian Lou, Lei Jiang
Neural Network Fairness Attack Speaker Verification Fairness Trojaned Model

November 12, 2023

Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithms
Kristof Meding, Thilo Hagendorff
Practical Algorithm Fairness Metric Malicious User Fair AI Fairness Attack

October 24, 2023

Deceptive Fairness Attacks on Graphs via Meta Learning
Jian Kang, Yinglong Xia, Ross Maciejewski, Jiebo Luo, Hanghang Tong
Graph Drawing Adversarial Robustness Graph Learning Model Fair Graph Fairness Attack

October 20, 2023

Adversarial Attacks on Fairness of Graph Neural Networks
Binchi Zhang, Yushun Dong, Chen Chen, Yada Zhu, Minnan Luo, Jundong Li
Graph Neural Network Adversarial Attack Procedural Fairness Fairness Aware Graph Fairness Attack

October 18, 2023

Revisiting Transferable Adversarial Image Examples: Attack Categorization, Evaluation Guidelines, and New Insights
Zhengyu Zhao, Hanwei Zhang, Renjue Li, Ronan Sicre, Laurent Amsaleg, Michael Backes, Qi Li, Chao Shen
Adversarial Example Evaluation Method Black Box Attack Transferable Attack New Insight Fairness Attack

August 31, 2023

One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions
Jan Simson, Florian Pfisterer, Christoph Kern
External Influence Algorithmic Fairness Fairness Implication Fairness Attack Model Decision