Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored DMs consistently generate a designated result (e.g., a harmful image) called backdoor target when the models' input contains a backdoor trigger. Although various backdoor techniques have been investigated to attack DMs, defense methods against these threats are still limited and underexplored, especially in inverting the backdoor trigger. In this paper, we introduce PureDiffusion, a novel backdoor defense framework that can efficiently detect backdoor attacks by inverting backdoor triggers embedded in DMs. Our extensive experiments on various trigger-target pairs show that PureDiffusion outperforms existing defense methods with a large gap in terms of fidelity (i.e., how much the inverted trigger resembles the original trigger) and backdoor success rate (i.e., the rate that the inverted trigger leads to the corresponding backdoor target). Notably, in certain cases, backdoor triggers inverted by PureDiffusion even achieve higher attack success rate than the original triggers.
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。
BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning
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);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);Department of Electronic and Electrical Engineering, University College London(伦敦大学学院电子与电气工程系)
Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World
NanJing University of Science and Technology(南京理工大学);University of Adelaide(阿德莱德大学);Data61, CSIRO(澳大利亚联邦科学与工业研究组织Data61);Sungkyunkwan University(成均馆大学)
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);National University of Singapore(新加坡国立大学);Nanyang Technological University(南洋理工大学);Sun Yat-sen University-Shenzhen(中山大学(深圳))
Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses
Warsaw University of Technology(华沙技术大学);NASK National Research Institute(国家研究机构NASK);IDEAS NCBR;IDEAS Research Institute(IDEAS研究所);Computer Vision Center, Universitat Autonoma de Barcelona(巴塞罗那自治大学计算机视觉中心)
BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts
Ministry of Education Key Lab for Intelligent Networks and Network Security(教育部长智能网络与网络安全重点实验室);Xi’an Jiaotong University(西安交通大学);INRIA(法国国家信息与自动化技术研究院);CFAR, A*STAR(新加坡A*STAR机构);Beijing Key Laboratory of Security and Privacy in Intelligent Transportation(北京智能交通安全与隐私重点实验室);Beijing Jiaotong University(北京交通大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);School of Cyber Engineering, Xi’an University of Electronic Science and Technology(西安电子科技大学网络安全工程学院);Ministry of Education Key Lab for Intelligent Networks and Network Security at Xi’an Jiaotong University(西安交通大学教育部长智能网络与网络安全重点实验室)
Backdoor Attack on Vertical Federated Graph Neural Network Learning
Fudan University(复旦大学);Nanjing University of Information Science and Technology(南京信息工程大学);Pennsylvania State University(宾夕法尼亚州立大学);Zhejiang University(浙江大学)
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)
Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
Nanjing University of Science and Technology(南京理工大学);The Hong Kong Polytechnic University(香港理工大学);University of Wollongong(沃林戈大学);The University of Western Australia(西澳大学)
FLARE: Toward Universal Dataset Purification against Backdoor Attacks
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);School of Information Technology, Deakin University(德克萨斯大学信息学院);School of Information and Communication Technology, Griffith University(格里菲斯大学信息与通信技术学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
School of Cyber Science and Engineering, Sichuan University(四川大学计算机科学与工程学院);School of Computer Science, China West Normal University(西南大学计算机科学学院);School of Electronic and Information Engineering, Lanzhou Jiaotong University(兰州交通大学电子信息工程学院)
Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises
School of Control and Computer Engineering, North China Electric Power University(控制与计算机工程学院,华北电力大学);Research Institute, China Unicom(中国unicom研究院);National Engineering Research Center of Next Generation Internet Broadband Service Application(下一代互联网宽带服务应用国家工程研究中心);College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)
DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);School of Mathematics, Sun Yat-sen University(中山大学数学学院);Zhejiang University(浙江大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新区(滨江)区块链与数据安全研究院);Tsinghua University(清华大学);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Research Center of Artificial Intelligence, Peng Cheng Laboratory(鹏城实验室人工智能研究中心)