LLM Backdoor Attacks

LLM: Large Language Model

Ask about this topic

Overview

Large language model backdoor research studies how hidden conditions—such as phrases, writing styles, dialogue history, or deployment settings—can make a model behave maliciously while appearing normal on ordinary inputs. Attacks use poisoned pretraining or fine-tuning data, weight and adapter edits, and compromised tools, memories, or retrieval systems; newer work also examines reasoning models, agents, and quantization. Defenses include trigger probing, activation and weight analysis, runtime monitoring, unlearning, pruning, and targeted model repair. A central challenge is detecting unknown or context-dependent backdoors across changing deployment conditions while preserving useful capabilities and safety.

Latest papers

CardsList

96 papers23 papers in the last four weeks, up 360% on the four weeks before. 0.1% of all new papers.

  1. 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

  2. Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning

    May 22, 2025Thibaud Gloaguen, Mark Vero, Robin Staab +1LLM Backdoor AttacksBackdoor Attacks

    ETH Zurich

  3. MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems

    Apr 23, 2025Mohaiminul Al Nahian, Zainab Altaweel, David Reitano +3LLM Backdoor AttacksLarge Language Model-Based Robot Planning

    Binghamton University (SUNY)

  4. 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

  5. BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

    Jun 3, 2024Jiaqi Xue, Mengxin Zheng, Yebowen Hu +3LLM Backdoor AttacksRAG Poisoning Attacks

    University of Central Florida · Emory University · Samsung Research America

  6. SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

    Feb 29, 2024Pengzhou Cheng, Wei Du, Zongru Wu +4Language Model PretrainingLLM Backdoor Attacks

    School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University · Department of Computer Science and Engineering Southern University of Science and Technology