arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.10686cs.CR
收藏

违规后恢复:针对泄露的DNN模型的白盒对抗示例的保护

Post-breach Recovery: Protection against White-box Adversarial Examples for Leaked DNN Models

Shawn Shan, Wenxin Ding, Emily Wenger, Haitao Zheng, Ben Y. Zhao

摘要:

服务器漏洞是当今互联网上一个不幸的现实。在深度神经网络(DNN)模型的背景下,它们特别有害,因为泄露的模型使攻击者能够“白盒”访问以生成对抗性示例,这种威胁模型没有实际的鲁棒防御。对于那些在专有DNN(例如医学成像)上投入了多年和数百万美元的从业者来说,这似乎是一场不可避免的灾难。在本文中,我们考虑DNN模型的违约后恢复问题。我们提出了Neo,这是一个新的系统,可以创建新版本的泄露模型,以及一个推理时间过滤器,可以检测和删除在以前泄露的模型上生成的对抗性示例。不同模型版本的分类表面略有偏移(通过引入隐藏分布),Neo检测到对其生成中使用的泄漏模型的过拟合攻击。我们表明,在各种任务和攻击方法中,Neo能够以非常高的准确性从泄露的模型中过滤出攻击,并提供强大的保护(7- 10次恢复),防止攻击者反复破坏服务器。Neo在各种强大的自适应攻击中表现出色,可恢复的漏洞数量略有下降,并展示了作为DNN防御的补充的潜力。

英文摘要:

Server breaches are an unfortunate reality on today's Internet. In the context of deep neural network (DNN) models, they are particularly harmful, because a leaked model gives an attacker "white-box" access to generate adversarial examples, a threat model that has no practical robust defenses. For practitioners who have invested years and millions into proprietary DNNs, e.g. medical imaging, this seems like an inevitable disaster looming on the horizon. In this paper, we consider the problem of post-breach recovery for DNN models. We propose Neo, a new system that creates new versions of leaked models, alongside an inference time filter that detects and removes adversarial examples generated on previously leaked models. The classification surfaces of different model versions are slightly offset (by introducing hidden distributions), and Neo detects the overfitting of attacks to the leaked model used in its generation. We show that across a variety of tasks and attack methods, Neo is able to filter out attacks from leaked models with very high accuracy, and provides strong protection (7--10 recoveries) against attackers who repeatedly breach the server. Neo performs well against a variety of strong adaptive attacks, dropping slightly in # of breaches recoverable, and demonstrates potential as a complement to DNN defenses in the wild.

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。

↑