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.
Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
Shanghai Jiao Tong University(上海交通大学);The University of Adelaide(阿德莱德大学);The University of New South Wales(新南威尔士大学);Data61 CSIRO(澳大利亚联邦科学与工业研究组织 Data61);Shanghai Institute for Advanced Communication and Data Science(上海先进通信与数据科学研究院);Shanghai University(上海大学)
POLAR: Policy-based Layerwise Reinforcement Learning Method for Stealthy Backdoor Attacks in Federated Learning
Columbia University(哥伦比亚大学);Shanghai Jiao Tong University(上海交通大学);Shanghai University of Electric Power(上海电力大学);National University of Singapore(新加坡国立大学);Stevens Institute of Technology(斯蒂文斯理工学院);Queen’s University Belfast(贝尔法斯特女王大学)
A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models
Singapore Management University(新加坡管理大学);China University of Mining and Technology(中国矿业大学);The University of Melbourne(墨尔本大学);Anhui University(安徽大学);Xi’an Jiaotong University(西安交通大学);Sun Yat-sen University(中山大学)
BadRSSD: Backdoor Attacks on Regularized Self-Supervised Diffusion Models
School of Information and Artificial Intelligence, Yangzhou University, China(扬州大学信息与人工智能学院);School of Computing and Artificial Intelligence, Chaohu University, China(池州学院计算机与人工智能学院);Tacoma School of Engineering and Technology, University of Washington, USA(华盛顿大学塔科马工程与技术学院)
Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning
Shandong Computer Science Center(山东计算机科学中心);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));College of computer science and technology, China University of Petroleum(中国石油大学计算机科学与技术学院);School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院);Big Data Institute, Qilu University of Technology(齐鲁工业大学大数据研究院)