Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
State Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院)
Self-supervised learning (SSL) is increasingly attractive for pre-training encoders without requiring labeled data. Downstream tasks built on top of those pre-trained encoders can achieve nearly state-of-the-art performance. The pre-trained encoders by SSL, however, are vulnerable to backdoor attacks as demonstrated by existing studies. Numerous backdoor mitigation techniques are designed for downstream task models. However, their effectiveness is impaired and limited when adapted to pre-trained encoders, due to the lack of label information when pre-training. To address backdoor attacks against pre-trained encoders, in this paper, we innovatively propose a mutual information guided backdoor mitigation technique, named MIMIC. MIMIC treats the potentially backdoored encoder as the teacher net and employs knowledge distillation to distill a clean student encoder from the teacher net. Different from existing knowledge distillation approaches, MIMIC initializes the student with random weights, inheriting no backdoors from teacher nets. Then MIMIC leverages mutual information between each layer and extracted features to locate where benign knowledge lies in the teacher net, with which distillation is deployed to clone clean features from teacher to student. We craft the distillation loss with two aspects, including clone loss and attention loss, aiming to mitigate backdoors and maintain encoder performance at the same time. Our evaluation conducted on two backdoor attacks in SSL demonstrates that MIMIC can significantly reduce the attack success rate by only utilizing <5% of clean data, surpassing seven state-of-the-art backdoor mitigation techniques.
Towards Understanding How Self-training Tolerates Data Backdoor Poisoning
University of Alberta(阿尔伯塔大学);Illinois Institute of Technology(伊利诺伊理工学院);Michigan State University(密歇根州立大学)
最近对模型训练中的后门攻击的研究表明,污染一小部分训练数据就足以在中毒的测试时间数据上产生不正确的操纵预测,同时在下游任务中保持高的干净精度。后门攻击的隐蔽性给当今的机器学习范式带来了巨大的防御挑战。在本文中,我们探索了通过额外的未标记数据进行自我训练以减轻后门攻击的潜力。我们首先进行了一项试点研究,以表明香草自我训练在后门缓解中无效。受此启发,我们建议通过在自训练伪标签阶段利用强大但适当的数据增强来防御后门攻击。我们发现,新的自我训练机制在很大程度上有助于抵御后门攻击。通过在CIFAR-10和CIFAR-10与额外的未标记的500 K TinyImages数据集的组合上针对不同后门触发器的实验,证明了其有效性。最后,我们探索了将自我监督表示学习与自我训练相结合的方向,以进一步改进后门防御。
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning
Polytechnique Montréal(蒙特利尔理工学院);Khalifa University(哈利法大学);Concordia Institute for Information Systems Engineering, Concordia University(康考迪亚大学康考迪亚信息系统工程研究所)
Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning
School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran(塔里斯坦大学电气与计算机工程学院);School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran(谢尔兹大学电气与计算机工程学院);Okinawa Institute of Science and Technology, Okinawa, Japan(冲绳科学技术研究院);School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran(基础科学研究院(IPM)计算机科学学院)
Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model
Zhejiang University of Technology(浙江工业大学);Institute of Cyberspace Security, Zhejiang University of Technology(浙江工业大学网络空间安全研究院);College of Information Engineering, Zhejiang University of Technology(浙江工业大学信息工程学院)
Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);School of Information and Communication Engineering, Dalian University of Technology(大连理工大学信息与通信工程学院);School of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
Dept. of Computer Science Faculty of Engineering University of Manchester Manchester, United Kingdom;Dept. of Computer Science Faculty of Engineering University of Manchester \& MBZUAI Abu Dhabi, United Arab Emirates;Dept. of Computer Science Faculty of Engineering University of Manchester \& KU Leuven Manchester, United Kingdom