视觉机器遗忘中的偏见再分配：遗忘一组是否损害另一组？
Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?
AI总结：
研究通过CLIP模型在CelebA数据集上探讨机器遗忘对偏见的再分配影响，发现遗忘某一性别群体会将偏见转移至相关群体，揭示嵌入空间中的性别主导结构。
摘要：
视觉机器遗忘中的偏见再分配：遗忘一组是否损害另一组？研究通过CLIP模型在CelebA数据集上探讨机器遗忘对偏见的再分配影响，发现遗忘某一性别群体会将偏见转移至相关群体，揭示嵌入空间中的性别主导结构。
英文摘要：
Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness implications remain underexplored: when a model forgets a demographic group, does it neutralize that concept or redistribute it to correlated groups, potentially amplifying bias? We investigate this bias redistribution phenomenon on CelebA using CLIP models (ViT/B-32, ViT-L/14, ViT-B/16) under a zero-shot classification setting across intersectional groups defined by age and gender. We evaluate three unlearning methods, Prompt Erasure, Prompt Reweighting, and Refusal Vector using per-group accuracy shifts, demographic parity gaps, and a redistribution score. Our results show that unlearning does not eliminate bias but redistributes it primarily along gender rather than age boundaries. In particular, removing the dominant Young Female group consistently transfers performance to Old Female across all model scales, revealing a gender-dominant structure in CLIP's embedding space. While the Refusal Vector method reduces redistribution, it fails to achieve complete forgetting and significantly degrades retained performance. These findings highlight a fundamental limitation of current unlearning methods: without accounting for embedding geometry, they risk amplifying bias in retained groups.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
