Backdoor Attacks

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, down 14% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 87

All topics

When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
Jul 13, 2026Yibo Hu, Ren WangBackdoor Attacks Backdoor Detection
Illinois Institute of Technology
Statistically Undetectable Backdoors in Deep Neural Networks
Jul 10, 2026Andrej Bogdanov, Alon Rosen, Neekon VafaBackdoor Attacks Adversarial Examples
University of Ottawa. · Bocconi University. · Massachusetts Institute of Technology.
Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection
Jul 10, 2026Jaesun Baek, Chanwook Lee, Eun-Kyu LeeBackdoor Attacks Spiking Neural Networks
Dept. of Information and Telecommunication Eng., Incheon National University, Republic of Korea
Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles
Jul 7, 2026Marwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzano +1Autonomous Driving Datasets Data Augmentation
SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris Palaiseau, France · Universidad Carlos III de Madrid Leganes, Spain
The Power of Backdoor Absorption in Community Training
Jul 7, 2026Issam Seddik, Sami Souihi, Mohamed Tamaazousti +1Algorithmic Auditing Backdoor Attacks
Université Paris-Saclay, CEA LIST, Palaiseau, France
Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor
Jul 7, 2026Qi Zhao, Christian WressneggerBackdoor Attacks Backdoor Detection
KASTEL Security Research Labs · Karlsruhe Institute of Technology (KIT)
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning
Jul 2, 2026Yueming Huang, Wenhan Yao, Fen Xiao +2Backdoor Attacks Deep Deterministic Policy Gradient
Xiangtan University, Yuhu District Xiangda Road, Xiangtan, 411100, Hunan, China · Peking University, No.5, Summer Palace Road, Haidian District, Beijing, China, Beijing, 100871, Beijing, China
Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack
Jul 2, 2026Yueming Huang, Wenhan Yao, Fen Xiao +2Backdoor Attacks
Xiangtan University, Yuhu District Xiangda Road, Xiangtan, 411100, Hunan, China · Peking University, No.5, Summer Palace Road, Haidian District, Beijing, China, Beijing, 100871, Beijing, China
Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel
Jun 29, 2026Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1Backdoor Attacks Semantic Communication
Nexcepta, Gaithersburg, MD, USA · The Ohio State University, Columbus, OH, USA · University of Maryland, College Park, MD, USA
Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System
Jun 27, 2026Thomas Thebaud, Sonal Joshi, Henry Li +4Backdoor Attacks Automatic Speech Recognition
Center for Language and Speech Processing, Johns Hopkins University, USA · Faculty of Information Technology, Brno University of Technology, Czechia
TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models
Jun 24, 2026William Aiken, Paula Branco, Guy-Vincent Jourdan +1Backdoor Attacks Diffusion-Based Image Generation
School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada
Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks
Jun 24, 2026Kavindu Herath, Joshua C. Zhao, Saurabh BagchiBackdoor Attacks Backdoor Attacks in Federated Learning
Department of Electrical and Computer Engineering, Purdue University, West Lafayette, USA
TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
Jun 22, 2026Vu Tuan Truong, Long Bao LeBackdoor Attacks Diffusion Models
INRS, University of Quebec
Rethinking Molecular Graph Backdoors under Chemistry-aware Admission
Jun 22, 2026Thinh T. H. Nguyen, Sze Jue Yang, Khoa D. Doan +2Graph Neural Networks Backdoor Attacks
VinUniversity, Hanoi, Vietnam · Universiti Malaya
CLIP-guided Diffusion Model for Backdoor Generation in Sensor-based Human Activity Recognition
Jun 22, 2026Toby Briston, Illya Kosyk, Kuniyih SHuman Activity Recognition Backdoor Attacks
BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Driving
Jun 19, 2026Zhe Shuai, Xiaopeng Xie, Yikun ZengBackdoor Attacks Autonomous Driving
Shanghai Jiao Tong University
Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning
Jun 19, 2026Yongbin Huang, Xihao Xie, Jia ZhangBackdoor Attacks Speech Emotion Recognition
Department of Computer Science Southern Methodist University Dallas, USA
Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection
Jun 18, 2026Ziba Parsons, Ang LiLidar-Based 3D Object Detection Backdoor Attacks
Computer and Information Science University of Michigan - Dearborn Dearborn, MI 48170
FloatDoor: Platform-Triggered Backdoors in LLMs
Jun 17, 2026Nils Loose, Jonas Sander, Felix Mächtle +1LLM Backdoor Attacks Backdoor Attacks
University of Luebeck
Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP Backdoors
Jun 16, 2026Kunlan Xiang, Haomiao Yang, Wenbo JiangVLM Robustness Adversarial Attacks on VLMs
University of Electronic Science and Technology of China
Continual Backdoor Training in IoT/CPS
Jun 12, 2026Oxana Salish, Kuniyilh SBackdoor Attacks Continual Learning
PolicyGuard: Towards Test-time and Step-level Adversary (Backdoor) Defense for Reinforcement Learning Agent
Jun 11, 2026Junfeng Guo Heng HuangBackdoor Attacks Backdoor Defense
Computer Science, University of Maryland College Park, USA.
Targeting World Models to Compromise Robot Learning Pipelines
Jun 8, 2026Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud +3Robot Policy Learning World Models for Robotics
Northeastern University · University of Massachusetts Amherst
Patcher: Post-Hoc Patching of Backdoored Large Language Models
Jun 2, 2026Anjun Gao, Yueyang Quan, Yufei Xia +2LLM Backdoor Attacks Backdoor Attacks
University of Louisville · University of North Texas
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
May 29, 2026Ziqing Yang, Rui Wen, Xinlei He +3Adversarial Attacks Backdoor Attacks
1CISPA Helmholtz Center for Information Security · Institute of Science Tokyo · 3Wuhan University +1
Density-aware Sample-specific Attack
May 27, 2026Qiyuan Wang, Yao Li, Raymond K. W. WongBackdoor Attacks Adversarial Robustness
Texas A&M University · University of North Carolina at Chapel Hill
Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems
May 26, 2026Abile Jean, Kuniyilh SCyber-Physical Systems Backdoor Attacks
When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
May 21, 2026Donald Flynn, Hadas Yaron Goldhirsh, Jonathan P. Keating +1Backdoor Attacks Statistical Learning Theory
1Mathematical Institute, University of Oxford · School of Mathematical Science, Tel Aviv University · School of Mathematical Science and Computer Science, Tel Aviv University
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
May 21, 2026Quang Duc Nguyen, Siyuan Liang, Yiming Li +2Backdoor Attacks Time Series Forecasting
College of Computing and Data Science, Nanyang Technological University, Singapore.
Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
May 20, 2026Yifei Wang, Yida Yang, Tianlin Li +3LLM Backdoor Attacks Backdoor Attacks
Shanghai Jiao Tong University · Tongji University · Beihang University +1

Jul 13, 2026, cs.CRJ/K move · Enter open · S save

When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems

Yibo Hu, Ren Wang

Illinois Institute of Technology

Backdoor Attacks Backdoor Detection AI Agent Monitoring Multi-Agent System Security

Open paper AskPDF arXiv

As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundamental hole. A distributed backdoor splits a harmful payload across agents, so every local check passes while the assembled object is the attack. The monitor can be right on every step and still miss the attack. The problem is not splitting itself: split fragments can still leak suspicious tokens or provenance edges. The hard case is \emph{local benignness}. No fragment carries the harm, and what is left looks like ordinary benign traffic. We formalize this as an \emph{observability boundary}: a monitor catches only what its view can tell apart from benign traffic. We prove that once the fragments look benign in the monitored view, no detector on that view can catch them, however strong it is. Across a controlled testbed, an external benchmark, and end-to-end agent runs, local monitors lose the signal exactly as local evidence disappears, and it returns only when the monitor sees the assembled object. A monitor trained only on benign traffic recovers the attack's code structure across held-out encodings (0.874 mean AUROC). A decoded-view gate, given the encoding family, blocks every tested attack. But seeing more is not enough: full-trace monitors and decoders still fail unless they reach the representation where the payload is exposed. Local safety is not global safety when harm is compositional, and the open problem is finding that representation.

Momentum

Related topics

Latest papers 87