BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916449418739712 |
|---|---|
| author | Xue, Jiaqi Lou, Qian Zheng, Mengxin |
| author_facet | Xue, Jiaqi Lou, Qian Zheng, Mengxin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_17492 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers Xue, Jiaqi Lou, Qian Zheng, Mengxin Cryptography and Security Computation and Language Computers and Society Machine Learning 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. |
| title | BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers |
| topic | Cryptography and Security Computation and Language Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2410.17492 |