mlsanityData to 7 Oct 2026

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

arXiv 2502.05224 ↗First posted 6 Feb 2025cs.CR cs.AIcited by 25

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural language processing (NLP) performance, considering their widespread usage in many industries, including medicine, finance, education, etc., security concerns over their usage grow simultaneously. In recent years, the evolution of backdoor attacks has progressed with the advancement of defense mechanisms against them and more well-developed features in the LLMs. In this paper, we adapt the general taxonomy for classifying machine learning attacks on one of the subdivisions - training-time white-box backdoor attacks. Besides systematically classifying attack methods, we also consider the corresponding defense methods against backdoor attacks. By providing an extensive summary of existing works, we hope this survey can serve as a guideline for inspiring future research that further extends the attack scenarios and creates a stronger defense against them for more robust LLMs.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. First posted on arXiv 6 Feb 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 7.

25 papers.

Sort:

By area:

  1. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasurescited by 93
  2. 2025AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agentscited by 25
  3. 2025Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulationcited by 13
  4. 2026The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggerscited by 13
  5. 2025ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Modelscited by 10
  6. 2025Backdoor Attribution: Elucidating and Controlling Backdoor in Language Modelscited by 8
  7. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 7
  8. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  9. 2025Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment through Latent Acoustic Pattern Triggerscited by 7
  10. 2025LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systemscited by 5
  11. 2025Pruning Strategies for Backdoor Defense in LLMscited by 4
  12. 2025Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilitiescited by 4
13 more
  1. 2025P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMscited by 4
  2. 2025DecepChain: Inducing Deceptive Reasoning in Large Language Modelscited by 3
  3. 2025Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Modelscited by 3
  4. 2026Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Rewardcited by 3
  5. 2025From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMscited by 2
  6. 2025SFL-LEO: Asynchronous Split-Federated Learning Design for LEO Satellite-Ground Network Frameworkcited by 1
  7. 2026Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggerscited by 1
  8. 2026IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requestscited by 1
  9. 2025Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Promptscited by 0
  10. 2025Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmeticcited by 0
  11. 2026On the Privacy of LLMs: An Ablation Studycited by 0
  12. 2026When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Modelscited by 0
  13. 2026Detecting Hidden Behaviors in LLMs via Activation-matched Finetuningcited by 0