arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.05077cs.LG
收藏

利用多级MMD正则化增强后门攻击

Enhancing Backdoor Attacks with Multi-Level MMD Regularization

University of Science and Technology of China(中国科学技术大学)

Pengfei Xia, Hongjing Niu, Ziqiang Li, Bin Li

摘要:

虽然深度神经网络(DNN)在许多任务中表现出色,但它们所需的巨大培训资源成为从业者开发自己模型的障碍。从互联网收集数据或雇佣第三方来训练模型已经变得很普遍。不幸的是,最近的研究表明,这些操作为恶意地将隐藏的后门注入DNN提供了可行的途径。已经开发了几种防御方法来检测恶意样本,通常假设由感染模型提取的良性和恶意样本的潜在表示呈现不同的分布。然而,缺乏对分配差异的全面研究。本文通过回答以下三个问题对这种差异进行了深入的研究:1)分布差异的特征是什么?2)如何才能有效地减少它们?3)这种减少对基于差异的防御方法有什么影响?首先,通过引入最大平均离散度(MMD),能量距离(ED)和切片Wasserstein距离(SWD)作为度量,验证了定期训练的后门模型上的多层表示的分布差异是显著的。然后,提出了一种在损失中加入多层MMD正则化的差异缩减方法ML-MMDR,并在三种典型的基于差异的防御方法上验证了其有效性。在所有的实验设置中,这些方法的F1分数从常规训练的后门模型的90%-100%下降到使用ML-MMDR训练的模型的60%-70%。这些结果表明,提出的MMD正则化可以提高现有的后门攻击方法的隐蔽性。我们的方法的原型代码现在可以在https://github.com/xpf/Multi-Level-MMD-Regularization上获得。

英文摘要:

While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become common to collect data from the Internet or hire a third party to train models. Unfortunately, recent studies have shown that these operations provide a viable pathway for maliciously injecting hidden backdoors into DNNs. Several defense methods have been developed to detect malicious samples, with the common assumption that the latent representations of benign and malicious samples extracted by the infected model exhibit different distributions. However, a comprehensive study on the distributional differences is missing. In this paper, we investigate such differences thoroughly via answering three questions: 1) What are the characteristics of the distributional differences? 2) How can they be effectively reduced? 3) What impact does this reduction have on difference-based defense methods? First, the distributional differences of multi-level representations on the regularly trained backdoored models are verified to be significant by introducing Maximum Mean Discrepancy (MMD), Energy Distance (ED), and Sliced Wasserstein Distance (SWD) as the metrics. Then, ML-MMDR, a difference reduction method that adds multi-level MMD regularization into the loss, is proposed, and its effectiveness is testified on three typical difference-based defense methods. Across all the experimental settings, the F1 scores of these methods drop from 90%-100% on the regularly trained backdoored models to 60%-70% on the models trained with ML-MMDR. These results indicate that the proposed MMD regularization can enhance the stealthiness of existing backdoor attack methods. The prototype code of our method is now available at https://github.com/xpf/Multi-Level-MMD-Regularization.

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。

↑