mlsanityData to 14 Oct 2026

BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers

arXiv 2410.17492 ↗First posted 23 Oct 2024cs.CR cs.CL cs.CYcited by 4

Not on the map. Why?

Abstract (arXiv)

Attacking fairness is crucial because compromised models can introduce biased outcomes, undermining trust and amplifying inequalities in sensitive applications like hiring, healthcare, and law enforcement. This highlights the urgent need to understand how fairness mechanisms can be exploited and to develop defenses that ensure both fairness and robustness. We introduce BadFair, a novel backdoored fairness attack methodology. BadFair stealthily crafts a model that operates with accuracy and fairness under regular conditions but, when activated by certain triggers, discriminates and produces incorrect results for specific groups. This type of attack is particularly stealthy and dangerous, as it circumvents existing fairness detection methods, maintaining an appearance of fairness in normal use. Our findings reveal that BadFair achieves a more than 85% attack success rate in attacks aimed at target groups on average while only incurring a minimal accuracy loss. Moreover, it consistently exhibits a significant discrimination score, distinguishing between pre-defined target and non-target attacked groups across various datasets and models.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 23 Oct 2024.

Builds on

33 of 49 references.

References · 33

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  4. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  5. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  6. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  7. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  8. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  9. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  10. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 412
  11. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  12. 2023Poisoning Language Models During Instruction Tuningcited by 269
21 more
  1. 2018Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systemscited by 234
  2. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 222
  3. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  4. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  5. 2020Subpopulation Data Poisoning Attackscited by 70
  6. 2020Poisoning Attacks on Algorithmic Fairnesscited by 59
  7. 2018Challenges for Toxic Comment Classification: An In-Depth Error Analysiscited by 56
  8. 2020Exacerbating Algorithmic Bias through Fairness Attackscited by 47
  9. 2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
  10. 2020On Adversarial Bias and the Robustness of Fair Machine Learningcited by 36
  11. 2021RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHRcited by 32
  12. 2023TrojText: Test-time Invisible Textual Trojan Insertioncited by 28
  13. 2021Estimating and Improving Fairness with Adversarial Learningcited by 26
  14. 2023Backdoor Learning on Sequence to Sequence Modelscited by 21
  15. 2021Poisoning Attacks on Fair Machine Learningcited by 19
  16. 2019Early Prediction of Alzheimer's Disease Dementia Based on Baseline Hippocampal MRI and 1-Year Follow-Up Cognitive Measures Using Deep Recurrent Neural Networkscited by 14
  17. 2023A benchmark for toxic comment classification on Civil Comments datasetcited by 11
  18. 2022ESTAS: Effective and Stable Trojan Attacks in Self-supervised Encoders with One Target Unlabelled Samplecited by 9
  19. 2023TrojFSP: Trojan Insertion in Few-shot Prompt Tuningcited by 9
  20. 2023Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Modelscited by 8
  21. 2023AI Gender Bias, Disparities, and Fairness: Does Training Data Matter?cited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attackscited by 8
  2. 2025Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Textscited by 5
  3. 2025In-Context Bias Propagation in LLM-Based Tabular Data Generationcited by 1
  4. 2026Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models
  2. 2023When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
  3. 2025Adversarial Bias: Data Poisoning Attacks on Fairness
  4. 2024Real is not True: Backdoor Attacks Against Deepfake Detection ↗
  5. 2023Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
  6. 2023Attacks on fairness in Federated Learning
  7. 2024Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
  8. 2025Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifiers