Backdoor Defense

Follow this topic Ask about this topic

Backdoor defense studies how to find and neutralize hidden behaviors implanted during training that cause a model to act maliciously when it encounters a trigger, while preserving normal performance. Methods include screening suspicious training examples, detecting or purifying triggered inputs, repairing or unlearning model components, robust training, and runtime monitoring; approaches are being developed for vision, language, speech, graphs, and reinforcement learning. A central challenge is that defenses often rely on clues from known triggers or model internals, so protection may not transfer to unfamiliar or adaptive attacks. Across settings, defenses must balance attack suppression with clean accuracy, task utility, and practical limits on data and model access.

Latest papers

50 papers7 papers in the last four weeks, up 17% on the four weeks before. 0.0% of all new papers.

RePAIR: Inverting Backdoor Attacks in Semantic Segmentation
Oct 27, 2026Arnold Brosch, Kira MaagBackdoor Defense Semantic Segmentation
Heinrich Heine University Düsseldorf
Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering
Oct 24, 2026Soumita Chatterjee, Sudip Ghosh, Tamal Ghosh +2Backdoor Defense Backdoor Detection
Indian Institute of Engineering Science and Technology, Shibpur, India
SemPurify: Semantics-Aware Data Purification for Black-box Backdoor Defense
Oct 16, 2026Jiawei Yu, Syed Irfan Ali Meerza, Yi Wu +2Backdoor Defense
University of Georgia · Virginia Commonwealth University · University of Oklahoma +1
Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
Oct 14, 2026Florian Spelter, Johannes F. Loevenich, Tobias Hürten +4Backdoor Attacks Data Poisoning Attacks
CortAIx Labs, Thales Deutschland, Ditzingen, Germany · Grey Solutions, Düsseldorf, Germany · Department of Mathematics/Computer Science, University of Osnabrück, Osnabrück, Germany +2
TARE: Weigh a Never-Poisoned Twin Before Reading Backdoor-Defense Costs
Oct 4, 2026Ruizhi Xu, Wei Xu, Sibo ZhuBackdoor Defense Benchmark Validity
School of Mathematics University of Edinburgh · Beijing Jinhe Technology Co., Ltd. · Inno Asset Management
Backdoor Containment via Expert Quarantine and Shutdown in LLMs
Sep 30, 2026Jianwei Li, Min-Seon Kim, Jung-Eun KimLLM Backdoor Attacks Backdoor Defense in LLMs
Department of Computer Science North Carolina State University Raleigh, NC 27606, USA
Selective Channel Restoration for Backdoored Vision-Language Models
Sep 29, 2026Shuming Liu, Zhifang Zhang, Suqin Yuan +3VLM Robustness Large Vision-Language Models
Southeast University · The University of Queensland · University of Sydney +1
Backdoor as Probe: Test-Time Adversarial Defense for CLIP
Sep 28, 2026Zhongqi Wang, Jie Zhang, Nie Sen +3VLM Robustness Backdoor Defense
Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Xuzhou University of Technology, China
Region-Level Black-Box Defense Against Stealthy Embedding-Space Backdoors in CLIP
Sep 25, 2026Ahmed Abdelnaby, Mohamed ElmahallawyBackdoor Defense VLM Robustness
Washington State University, Richland, WA 99354, USA
ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus
Sep 23, 2026Li Zeng, Mingcheng Duan, Longfei Fan +5Backdoor Attacks Backdoor Defense
School of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410114, China · School of Computer Science, Xiangtan University, Xiangtan 411105, China · School of Software, Yunnan University, Kunming 650500, China +3
Backdoors in Learning-Based Industrial Robotic Arm Manipulation: An Empirical Security Study
Sep 22, 2026Zijian Zhang, Zhen Zeng, Zhongshu Gu +1Backdoor Defense Robotic Manipulation
Department of Computer Science, University of Wisconsin Milwaukee, Milwaukee, WI, USA · IBM Research, Yorktown Heights, NY, USA · MIT Lincoln Laboratory, Lexington, MA, USA
Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery
Sep 6, 2026Keyu Lin, Fei Ye, Qihe Liu +2Incremental Learning Backdoor Defense
University of Electronic Science and Technology of China, Chengdu 610054, China
Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers
Sep 2, 2026Ahmed Abdelnaby, Mohamed ElmahallawyBackdoor Detection Backdoor Defense
School of Engineering and Applied Sciences, Washington State University, Richland, WA 99354, USA
GhostWord: A Fine-Grained Backdoor Attack on Automatic Speech Recognition
Sep 2, 2026Mojtaba Nafez, Mobina Poulaei, Kiarash Kiani Feriz +4Backdoor Attacks Automatic Speech Recognition
Sharif University of Technology · Isfahan University
DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors
Aug 26, 2026Tuo Chen, Jie Gui, Minjing Dong +4Backdoor Defense Backdoor Attacks on VLMs
School of Cyber Science and Engineering Southeast University Nanjing, China · Ant Group Hangzhou, China · Purple Mountain Laboratories Nanjing, China +3
Backdoor Decontamination Dynamics in LLM Agents
Aug 11, 2026Gabriel Huang, Abhay Puri, Léo Boisvert +4LLM Backdoor Attacks Backdoor Defense in LLMs
ServiceNow Research · Mila – Quebec AI Institute · Polytechnique Montréal +3
DiffSafeMerge: Mitigating Backdoor Inheritance in Diffusion Model Merging
Aug 10, 2026Jiayang Zhang, Ji Guo, Jiachen Li +2Backdoor Attacks Backdoor Defense
University of Electronic Science and Technology of China, Chengdu, China · Wuhan University of Technology, Wuhan, China
Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling
Aug 1, 2026Zixuan Zhu, Rui Wang, Lihua Jing +1Backdoor Attacks Backdoor Defense
Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences
Anti-Backdoor Coreset Selection via Cumulative Entropy
Jul 28, 2026Qi Zhao, Christian WressneggerNeural Network Robustness Training Data Selection
KASTEL Security Research Labs, Karlsruhe Institute of Technology (KIT)
SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models
Jul 17, 2026Jinwen Xin, Xixiang LvBackdoor Detection Automatic Speech Recognition
School of Cyber Engineering Xidian University Xi’an, China
ORAN-DEFEND: Subspace Detection and Sanitization of Backdoor DRL xApps in Open RAN
Jul 7, 2026Md Raihan Uddin, Fatemeh Lotfi, Tolunay Seyfi +1Adversarial Attacks Backdoor Detection
Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA
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)
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
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
InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset
Jun 14, 2026Zhenyu YuBackdoor Defense Machine Unlearning
College of Computer Science and Artificial Intelligence Fudan University
Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning
Jun 12, 2026Zhenqian Zhu, Yamin Hu, Yujiang Liu +5Backdoor Defense Machine Unlearning
Harbin Institute of Technology, Shenzhen Shenzhen, Guangdong, China · Shenzhen Key Laboratory of Media Security, Shenzhen University Shenzhen, Guangdong, China
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.
Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMs
Jun 10, 2026Kazuki Iwahana, Masaru Matsubayashi, Takuma Koyama +3LLM Backdoor Attacks Backdoor Defense in LLMs
NTT Social Informatics Laboratories · Tohoku University

Oct 27, 2026J/K move · Enter open · S save

RePAIR: Inverting Backdoor Attacks in Semantic Segmentation

Arnold Brosch, Kira Maag

Heinrich Heine University Düsseldorf

Backdoor Defense Semantic Segmentation

Open paper AskPDF arXiv

Despite significant advances in computer vision, semantic segmentation models remain vulnerable to backdoor attacks, posing a security risk. These attacks redirect pixels of a chosen victim class to an attacker-specified target class when a trigger is present, while preserving clean predictions. Existing defenses are largely derived from image classification, while dedicated segmentation defenses remain scarce and typically require retraining or model modification. We introduce RePAIR, a post-hoc, label-free, attack-unaware defense based on the observation that backdoor-induced shifts can be stronger in the classifier head than in internal representations, leaving recoverable victim-class semantics. RePAIR infers the victim-target relation from an unlabeled, potentially contaminated image pool, constructs a safety-approved semantic reference, and localizes suspicious pixels by comparing head predictions with internal semantic evidence. It then applies feature-space and output corrections toward the inferred victim semantics, while conservative localization and output constraints limit changes to benign predictions. We model the attack as adversarial probability transport and repair as its approximate reversal, deriving bounds and sufficient conditions for localization, residual attack success, clean-side changes, defense-induced target predictions, and attack-unaware pair identification. Experiments across segmentation architectures and attack settings show that RePAIR substantially reduces attack success while largely preserving clean performance.