A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
School of Cybersecurity, Northwestern Polytechnical University(西北工业大学网络空间安全学院);Research & Development Institute of Northwestern Polytechnical University in Shenzhen(西北工业大学深圳研究院)
Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will perform abnormal actions leading to failures or malicious goals. However, existing proposed backdoors suffer from several issues, e.g., fixed visual trigger patterns lack stealthiness, the backdoor is trained or activated by an additional network, or all agents are backdoored. To this end, in this paper, we propose a novel backdoor attack against c-MADRL, which attacks the entire multi-agent team by embedding the backdoor only in a single agent. Firstly, we introduce adversary spatiotemporal behavior patterns as the backdoor trigger rather than manual-injected fixed visual patterns or instant status and control the attack duration. This method can guarantee the stealthiness and practicality of injected backdoors. Secondly, we hack the original reward function of the backdoored agent via reward reverse and unilateral guidance during training to ensure its adverse influence on the entire team. We evaluate our backdoor attacks on two classic c-MADRL algorithms VDN and QMIX, in a popular c-MADRL environment SMAC. The experimental results demonstrate that our backdoor attacks are able to reach a high attack success rate (91.6\%) while maintaining a low clean performance variance rate (3.7\%).
BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning
University of Chinese Academy of Sciences(中国科学院大学);INRIA(法国国家信息与自动化研究所);Microsoft Azure AI(微软Azure人工智能);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
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)
STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning
Singapore Institute of Technology (SIT)(新加坡理工学院(SIT));SingHealth Duke-NUS AI in Medicine Institute(新加坡保健服务集团杜克-新加坡国立大学医学院AI研究所);SingHealth AI Office(新加坡保健服务集团AI办公室)
SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院);National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University(西安交通大学人机混合增强智能全国重点实验室)
Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models
Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing 100190, China, and also with the University of Chinese Academy of Sciences (UCAS), Beijing 100049, China(中国科学院人工智能安全重点实验室,计算技术研究所(ICT),中国科学院(CAS),北京100190,中国,以及中国科学院大学(UCAS),北京100049,中国)
VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation
University of Science and Technology of China(中国科学技术大学);National University of Singapore(新加坡国立大学);East China University of Science and Technology(东华大学)
BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
Laboratory Of Intelligent Collaborative Computing, University of Electronic Science and Technology of China(智能协同计算实验室,电子科技大学);School of Computer Science and Technology, Xinjiang University(计算机科学与技术学院,新疆大学);School of Computer Science and Engineering, University of Electronic Science and Technology of China(计算机科学与工程学院,电子科技大学);School of Computer Science, Fudan University(计算机科学学院,复旦大学)
The Pennsylvania State University(宾夕法尼亚州立大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California, Santa Barbara(加州大学圣巴巴拉分校);University of Georgia(佐治亚大学);University of California Berkeley(加州大学伯克利分校)
DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
Qatar Computing Research Institute, Hamad Bin Khalifa University(卡塔尔计算研究所,哈马德·本·哈利法大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Towards Backdoor Stealthiness in Model Parameter Space
Radboud University(拉德博德大学);Delft University of Technology(代尔夫特理工大学);Radboud University, Nijmegen, The Netherlands(拉德博德大学);University of Zagreb Faculty of Electrical Engineering and Computing(Zagreb 工程与计算学院)
GaussTrap: Stealthy Backdoor Attacks on 3D Gaussian Splatting for Targeted Scene Misperception
Harbin Institute of Technology(Shenzhen)(哈尔滨工业大学(深圳));South China University of Technology(华南理工大学);Harbin Institute of Technology(哈尔滨工业大学);Shenzhen Internation Graduate School, Tsinghua University(深圳国际研究生院,清华大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));Huawei Manufacturing(华为制造)
CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
School of Information Sciences, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校信息科学学院);College of Information Engineering, Zhejiang University of Technology(浙江工业大学信息工程学院);Institute of Cyberspace Security, Zhejiang University of Technology(浙江工业大学网络空间安全研究院)
Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs
Department of Electronics Engineering, Tsinghua University, Beijing, China(清华大学电子工程系);College of AI, Tsinghua University, Beijing, China(清华大学人工智能学院);Beijing National Research Center for Information Science and Technology, Beijing, China(北京信息科学国家研究中心)