arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.01082cs.CR
收藏

针对语义分割模型的成员推断攻击

Membership Inference Attacks Against Semantic Segmentation Models

Tomas Chobola, Dmitrii Usynin, Georgios Kaissis

摘要:

成员推断攻击旨在通过观察其预测来推断数据记录是否已被用于训练目标模型。在医疗保健等敏感领域,这可能构成严重的隐私侵犯。在这项工作中,我们试图解决现有的知识差距进行了详尽的研究,成员推断攻击和防御领域的语义图像分割。我们的研究结果表明,对于某些威胁模型,这些学习设置可能比以前考虑的分类设置更容易受到攻击。我们还调查了一个威胁模型,一个不诚实的对手可以执行模型中毒,以帮助他们的推理和评估的影响,这些适应成员推断攻击的成功。我们定量评估了一些流行的模型架构在各种语义分割任务的攻击,证明在这个领域的成员推断攻击可以达到很高的成功率和防御他们可能会导致不利的隐私效用权衡或增加计算成本。

英文摘要:

Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we attempt to address the existing knowledge gap by conducting an exhaustive study of membership inference attacks and defences in the domain of semantic image segmentation. Our findings indicate that for certain threat models, these learning settings can be considerably more vulnerable than the previously considered classification settings. We additionally investigate a threat model where a dishonest adversary can perform model poisoning to aid their inference and evaluate the effects that these adaptations have on the success of membership inference attacks. We quantitatively evaluate the attacks on a number of popular model architectures across a variety of semantic segmentation tasks, demonstrating that membership inference attacks in this domain can achieve a high success rate and defending against them may result in unfavourable privacy-utility trade-offs or increased computational costs.

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。

↑