A backdoor attack in deep learning inserts a hidden backdoor in the model to trigger malicious behavior upon specific input patterns. Existing detection approaches assume a metric space (for either the original inputs or their latent representations) in which normal samples and malicious samples are separable. We show that this assumption has a severe limitation by introducing a novel SSDT (Source-Specific and Dynamic-Triggers) backdoor, which obscures the difference between normal samples and malicious samples.
To overcome this limitation, we move beyond looking for a perfect metric space that would work for different deep-learning models, and instead resort to more robust topological constructs. We propose TED (Topological Evolution Dynamics) as a model-agnostic basis for robust backdoor detection. The main idea of TED is to view a deep-learning model as a dynamical system that evolves inputs to outputs. In such a dynamical system, a benign input follows a natural evolution trajectory similar to other benign inputs. In contrast, a malicious sample displays a distinct trajectory, since it starts close to benign samples but eventually shifts towards the neighborhood of attacker-specified target samples to activate the backdoor.
Extensive evaluations are conducted on vision and natural language datasets across different network architectures. The results demonstrate that TED not only achieves a high detection rate, but also significantly outperforms existing state-of-the-art detection approaches, particularly in addressing the sophisticated SSDT attack. The code to reproduce the results is made public on GitHub.
Robust Backdoor Attacks against Deep Neural Networks in Real Physical World
Nanjing University of Aeronautics and Astronautics(南京航空航天大学)
深度神经网络(DNN)已被广泛部署在各种应用中。然而,许多研究表明,DNN是容易受到后门攻击。攻击者可以在目标DNN模型中创建一个隐藏的后门,并通过提交特定的后门实例来触发恶意行为。然而,现有的后门攻击研究大多集中在数字领域,而对真实物理世界中的后门攻击研究较少。受限于各种物理约束,后门攻击在真实物理世界中的性能会严重下降。本文提出了一种鲁棒的物理后门攻击方法PTB(physical transformations for backdoors),用于实现对真实物理世界中的深度学习模型的后门攻击。具体来说,在训练阶段,我们在每一轮模型训练中对这些注入的后门实例执行一系列物理变换,以模拟后门在现实世界中可能经历的各种变换,从而提高其物理鲁棒性。在最新的人脸识别模型上的实验结果表明,与不带PTB的后门攻击方法相比,该方法能够显著提高真实物理世界中的后门攻击性能.在各种复杂的物理条件下,通过仅注入非常小比例(0.5%)的后门实例,使用PTB方法对VGGFace进行物理后门攻击的攻击成功率为82%,而不使用所提出的PTB方法的后门攻击的攻击成功率低于11%。同时,目标DNN模型的正常性能没有受到影响。
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Deakin University(德肯大学);Beijing Normal-Hong Kong Baptist University(北京师范大学-香港 Baptist大学);University of New South Wales(新南威尔士大学);Griffith University(格里菲斯大学)
University of Science and Technology of China(中国科学技术大学);Microsoft Research(微软研究院);Beijing Electronic Science and Technology Institute(北京电子科技学院);Wormpex AI Research LLC(Wormpex人工智能研究有限责任公司)
Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures
Nanjing University of Science and Technology(南京理工大学);The University of Adelaide(阿德莱德大学);Data61, CSIRO(联邦科学与工业研究组织数据61研究所)
由于深度学习(DL)后门攻击已被发现是最阴险的对抗攻击之一,因此已经开发了一些对策,并在其各自的威胁模型中定义了某些假设。然而,这些对策的鲁棒性被无意中忽略,这可能会带来严重的后果,例如,对策可能被误用并导致后门检测的错误暗示。这是第一次,我们批判性地研究了现有后门对策的鲁棒性,最初关注的是三个有影响力的模型检查,即神经清洗(S& P '19),ABS(CCS'19)和MNTD(S& P '21)。虽然这三种对策声称它们在各自的威胁模型下工作良好,但它们具有固有的未探索的非鲁棒性情况,这取决于给定的任务,模型架构,数据集和防御超参数等因素,这些因素是\textit{not even rooted from delicate adaptive attacks}。我们演示了如何通过简单地改变上述因素来绕过它们,并与它们各自的威胁模型保持一致。特别地,对于每一个防御,形式证明或实证研究被用来揭示其两个非鲁棒的情况下,它是不作为强大的,因为它声称或期望,特别是最近的MNTD。这项工作突出了彻底评估后门对策的鲁棒性,以避免其误导性的安全影响,在未知的非强大的情况下的必要性。
School of Computer Science and Engineering, Changchun University of Technology(长春工业大学计算机科学与工程学院);AI Research Institute, Changchun University of Technology(长春工业大学人工智能研究院);School of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院)
HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning
School of Information Engineering, Yangzhou University(扬州大学信息工程学院);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Computing and Artificial Intelligence, Chaohu University(巢湖学院计算与人工智能学院);College of Data Science, Jiaxing University(嘉兴大学数据科学学院);Tacoma School of Engineering and Technology, University of Washington(华盛顿大学塔科马工程技术学院)
Tsinghua University(清华大学);Shandong University(山东大学);Wuhan University(武汉大学);Zhongguancun Laboratory(中关村实验室);Shandong Institute of Blockchain(山东省区块链研究院);National Financial Cryptography Research Center(国家金融密码研究中心)
Imperceptible and Robust Backdoor Attack in 3D Point Cloud
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Peng Cheng Laboratory(鹏城实验室);School of Data Science, the Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)(香港中文大学(深圳)数据科学学院);Shenzhen Research Institute of Big Data (SBRID)(深圳大数据研究院)
Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
Huazhong University of Science and Technology(华中科技大学);National Engineering Research Center for Big Data Technology and System(大数据技术与系统国家工程研究中心);Wuhan University(武汉大学)
An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers
Nanyang Technological University(南洋理工大学);Hong Kong University of Science and Technology(香港科技大学);Wuhan Textile University(武汉纺织大学);Zhejiang University(浙江大学);Wuhan University(武汉大学)
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Nanyang Technological University(南洋理工大学);Sun Yat-sen University-Shenzhen(中山大学深圳校区)
BadDet+: Robust Backdoor Attacks for Object Detection
School of Computer Science, Queensland University of Technology, Brisbane Australia(昆士兰科技大学计算机科学学院);Industrial Research Organisation, Pullenvale QLD, Australia(工业研究组织);Centre for Robotics, Queensland University of Technology, Brisbane Australia(机器人中心)
Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior
Nanyang Technological University(南洋理工大学);Pengcheng Laboratory(鹏城实验室);School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电气与电子工程学院);School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院);School of Computer Science, Peking University(北京大学计算机学院)
Cryptographic Backdoor for Neural Networks: Boon and Bane
College of Computing and Data Science, Nanyang Technological University Singapore(南洋理工大学计算与数据科学学院);Applied Statistics Unit, Indian Statistical Institute(印度统计研究所应用统计单位)
Fast and Lightweight Backdoor Detection via Head Random Probing
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(南京航空航天大学人工智能学院);School of Cybersecurity, Northwestern Polytechnical University(西北工业大学网络安全学院);Shenzhen Research Institute of Northwestern Polytechnical University(西北工业大学深圳研究院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院)
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
School of Data Science, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))