Perturbation Effects on Accuracy and Fairness among Similar Individuals
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_ | 1866910274125037568 |
|---|---|
| author | Li, Xuran Xue, Hao Wu, Peng Ma, Xingjun Zhang, Zhen Chen, Huaming Salim, Flora D. |
| author_facet | Li, Xuran Xue, Hao Wu, Peng Ma, Xingjun Zhang, Zhen Chen, Huaming Salim, Flora D. |
| contents | Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings. However, existing evaluation protocols typically assess these dimensions in isolation, thereby obscuring critical failure modes. To bridge this gap, we formalize Robust Individual Fairness (RIF): under semantic-preserving (truth-condition-preserving) perturbations, predictions should remain both correct with respect to the ground truth and invariant across semantically equivalent individuals. To surface RIF violations in practice, we introduce RIFair, a black-box adversarial framework that leverages a decoupled perturbation strategy to construct semantically preserved yet unrobust and/or unfair instance pairs. Experiments across multiple model architectures and real-world textual datasets show that robustness-only or fairness-only metrics often miss Robust Biased and Unrobust Fair behaviors. RIFair}reliably exposes these hidden vulnerabilities, supporting RIF as a necessary criterion for trustworthy model assessment. The experimental code is publicly available at https://github.com/Xuran-LI/RIFair. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01356 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Perturbation Effects on Accuracy and Fairness among Similar Individuals Li, Xuran Xue, Hao Wu, Peng Ma, Xingjun Zhang, Zhen Chen, Huaming Salim, Flora D. Machine Learning Artificial Intelligence Computers and Society Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings. However, existing evaluation protocols typically assess these dimensions in isolation, thereby obscuring critical failure modes. To bridge this gap, we formalize Robust Individual Fairness (RIF): under semantic-preserving (truth-condition-preserving) perturbations, predictions should remain both correct with respect to the ground truth and invariant across semantically equivalent individuals. To surface RIF violations in practice, we introduce RIFair, a black-box adversarial framework that leverages a decoupled perturbation strategy to construct semantically preserved yet unrobust and/or unfair instance pairs. Experiments across multiple model architectures and real-world textual datasets show that robustness-only or fairness-only metrics often miss Robust Biased and Unrobust Fair behaviors. RIFair}reliably exposes these hidden vulnerabilities, supporting RIF as a necessary criterion for trustworthy model assessment. The experimental code is publicly available at https://github.com/Xuran-LI/RIFair. |
| title | Perturbation Effects on Accuracy and Fairness among Similar Individuals |
| topic | Machine Learning Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2404.01356 |