提出新方法让模型在迁移时自动遗忘源域专属信息，保护数据隐私。
$\oslash$ Source Models Leak What They Shouldn't $\nrightarrow$: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
- 用对抗生成的遗忘样本，在适配过程中主动抹除源域特有知识。
- 在多个基准数据集上实现接近重训练的遗忘效果，性能超越基线。
- 适用于源数据不可见、类别未知或持续学习场景，实用性强。
视觉模型在卫星图像、医学扫描等跨域应用中日益普及，带来新隐私风险：模型可能无意中保留并泄露源域特有信息。尤其在无源数据域适应（SFDA）场景下，源模型虽未暴露数据，其影响仍可能渗入目标域。实验发现，现有SFDA方法在目标域上对源域独有类仍具强零样本识别能力，表明存在知识泄漏。为此提出新无学习设置SCADA-UL：在域适应中遗忘源域专属类别。设计一种新型重标定标签策略与对抗优化机制，通过对抗生成遗忘样本实现模型去学习。扩展至持续学习与未知类别遗忘场景。理论分析结合实证结果表明，该方法在基准数据集上持续优于基线，达到重训练级遗忘效果。代码已开源。
原文摘要 · Abstract (English)
The increasing adaptation of vision models across domains, such as satellite imagery and medical scans, has raised an emerging privacy risk: models may inadvertently retain and leak sensitive source-domain specific information in the target domain. This creates a compelling use case for machine unlearning to protect the privacy of sensitive source-domain data. Among adaptation techniques, source-free domain adaptation (SFDA) calls for an urgent need for machine unlearning (MU), where the source data itself is protected, yet the source model exposed during adaptation encodes its influence. Our experiments reveal that existing SFDA methods exhibit strong zero-shot performance on source-exclusive classes in the target domain, indicating they inadvertently leak knowledge of these classes into the target domain, even when they are not represented in the target data. We identify and address this risk by proposing an MU setting called SCADA-UL: Unlearning Source-exclusive ClAsses in Domain Adaptation. Existing MU methods do not address this setting as they are not designed to handle data distribution shifts. We propose a new unlearning method, where an adversarially generated forget class sample is unlearned by the model during the domain adaptation process using a novel rescaled labeling strategy and adversarial optimization. We also extend our study to two variants: a continual version of this problem setting and to one where the specific source classes to be forgotten may be unknown. Alongside theoretical interpretations, our comprehensive empirical results show that our method consistently outperforms baselines in the proposed setting while achieving retraining-level unlearning performance on benchmark datasets. Our code is available at https://github.com/D-Arnav/SCADA
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。