Backdoor Defense in LLMs

LLM: Large Language Model

Ask about this topic

Overview

Backdoor defense studies how to find and neutralize hidden trigger-response behaviors planted through poisoned training data, fine-tuning, or model adapters. Methods include adversarial training and unlearning, weight or neuron repair, activation-based analysis, and runtime monitoring of signals such as entropy, attention, and hidden-state changes. Researchers evaluate these defenses on trigger-activated attack success as well as clean task performance, including in multimodal models, tool-using agents, and quantized or federated settings. A central challenge is defending against unknown or adaptive triggers without raising false alarms, damaging useful behavior, or adding unacceptable inference cost.

Latest papers

CardsList

42 papers12 papers in the last four weeks, up 300% on the four weeks before. 0.1% of all new papers.

  1. Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models

    Apr 27, 2026Nay Myat Min, Long H. Pham, Jun SunLLM Backdoor AttacksAdversarial Attacks on LLMs

    Singapore Management University

  2. Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing

    Apr 27, 2026Kaisheng Fan, Weizhe Zhang, Yishu Gao +2LLM Backdoor AttacksBackdoor Defense in LLMs

    School of Cyber Science and Technology Harbin Institute of Technology Harbin, China · Department of New Networks Peng Cheng Laboratory Shenzhen, China · SnT University of Luxembourg Luxembourg City, Luxembourg

  3. Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models

    Apr 12, 2026Vu Tuan Truong, Long Bao LeBackdoor Defense in LLMsLLM Backdoor Attacks

    INRS, University of Quebec

  4. Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs

    Apr 12, 2026Eric Easley, Sebastian FarquharBackdoor Defense in LLMsLLM Jailbreak Attacks

    ML Alignment & Theory Scholars Berkeley, CA, USA · OATML, Department of Computer Science University of Oxford, Oxford, UK

  5. A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models

    Apr 6, 2026Tianmeng Fang, Yong Wang, Zetai Kong +4Backdoor Defense in LLMsLLM Security

    School of Computing and Information Systems, Singapore Management University, Singapore, 178902, , Singapore. · School of Artificial Intelligence, China University of Mining and Technology, Beijing, 102206, Beijing, PR China. · Faculty of Arts, The University of Melbourne, Melbourne, Carlton VIC 3053, Australia. +3

  6. From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems

    Apr 4, 2026Mingyang Xie, Jin Wei-KocsisLLM Backdoor AttacksLanguage Model-Based Control

    School of Applied and Creative Computing, Purdue University, West Lafayette, IN, USA

  7. BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator

    Mar 16, 2026Ruyi Zhang, Heng Gao, Songlei Jian +2Backdoor Defense in LLMsLLM Backdoor Attacks

    National University of Defense Technology, Changsha, Hunan, China

  8. Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference

    Mar 13, 2026Jianwei Li, Jung-Eun KimBackdoor Defense in LLMsLLM Backdoor Attacks

    Department of Computer Science, North Carolina State University, Raleigh, NA 27606, USA

  9. DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern

    Mar 2, 2026Xiaoyi Pang, Xuanyi Hao, Pengyu Liu +3LLM SecurityBackdoor Defense in LLMs

    The Hong Kong University of Science and Technology, Hong Kong · The State Key Laboratory of Blockchain and Data Security, Zhejiang University, P. R. China · School of Cyber Science and Technology, Zhejiang University, P. R. China

  10. Weight space Detection of Backdoors in LoRA Adapters

    Feb 16, 2026David Puertolas Merenciano, Ekaterina Vasyagina, Kevin Zhu +2Backdoor DetectionBackdoor Defense in LLMs

    Algoverse AI Research · Independent

  11. Optimizing Spectral Signature in Code Backdoor Detection

    Oct 15, 2025Quoc Hung Le, Thanh Le-Cong, Bach Le +1Backdoor DetectionBackdoor Defense in LLMs

    North Carolina State University, Raleigh, USA · The University of Melbourne, Melbourne, Australia

  12. UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models

    Feb 18, 2025Huawei Lin, Yingjie Lao, Tony Geng +2LLM Backdoor AttacksAdversarial Attacks on LLMs

    Rochester Institute of Technology · Tufts University · University of Rochester +1