# BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

arXiv: https://arxiv.org/abs/2408.12798 · HTML: https://mlsanity.com/paper/2408.12798/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers](https://mlsanity.com/paper/2106.15772/) (2021)
- [Anti-Backdoor Learning: Training Clean Models on Poisoned Data](https://mlsanity.com/paper/2110.11571/) (2021)
- [BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements](https://mlsanity.com/paper/2006.01043/) (2020)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection](https://mlsanity.com/paper/2307.16888/) (2023)
- [BackdoorBench: A Comprehensive Benchmark of Backdoor Learning](https://mlsanity.com/paper/2206.12654/) (2022)
- [Universal Jailbreak Backdoors from Poisoned Human Feedback](https://mlsanity.com/paper/2311.14455/) (2023)
- [A Thorough Examination of Decoding Methods in the Era of LLMs](https://mlsanity.com/paper/2402.06925/) (2024)
- [Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2305.14710/) (2023)
- [BadEdit: Backdooring large language models by model editing](https://mlsanity.com/paper/2403.13355/) (2024)

## Built on by (most cited first, 30 of 50)

- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents](https://mlsanity.com/paper/2411.09523/) (2024)
- [A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models](https://mlsanity.com/paper/2509.03871/) (2025)
- [BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents](https://mlsanity.com/paper/2601.04566/) (2026)
- [A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework](https://mlsanity.com/paper/2604.23338/) (2026)
- [BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit](https://mlsanity.com/paper/2507.18305/) (2025)
- [Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs](https://mlsanity.com/paper/2508.00161/) (2025)
- [AutoBackdoor: Automating Backdoor Attacks via LLM Agents](https://mlsanity.com/paper/2511.16709/) (2025)
- [Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference](https://mlsanity.com/paper/2603.13461/) (2026)
- [Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics](https://mlsanity.com/paper/2504.00446/) (2025)
- [When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment](https://mlsanity.com/paper/2506.07452/) (2025)
- [Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning](https://mlsanity.com/paper/2510.17021/) (2025)
- [Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation](https://mlsanity.com/paper/2510.18541/) (2025)
- [Model-Editing-Based Jailbreak against Safety-aligned Large Language Models](https://mlsanity.com/paper/2412.08201/) (2024)
- [Thought Purity: A Defense Framework For Chain-of-Thought Attack](https://mlsanity.com/paper/2507.12314/) (2025)
- [Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing](https://mlsanity.com/paper/2510.02334/) (2025)
- [Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI](https://mlsanity.com/paper/2603.07466/) (2026)
- [PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs](https://mlsanity.com/paper/2605.23168/) (2026)
- [On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs](https://mlsanity.com/paper/2412.20087/) (2024)
- [MobiLLM: An Agentic AI Framework for Closed-Loop Threat Mitigation in 6G Open RANs](https://mlsanity.com/paper/2509.21634/) (2025)
- [Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models](https://mlsanity.com/paper/2602.22246/) (2026)
- [Key-Conditioned Orthonormal Transform Gating (K-OTG): Multi-Key Access Control with Hidden-State Scrambling for LoRA-Tuned Models](https://mlsanity.com/paper/2512.17519/) (2025)
- [Backdooring Bias in Large Language Models](https://mlsanity.com/paper/2602.13427/) (2026)
- [Toward Reliable, Safe, and Secure LLMs for Scientific Applications](https://mlsanity.com/paper/2603.18235/) (2026)
- [Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers](https://mlsanity.com/paper/2604.21700/) (2026)
- [Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models](https://mlsanity.com/paper/2604.24542/) (2026)
- [Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions](https://mlsanity.com/paper/2605.25073/) (2026)
- [RogueMerge: Robust and Unified Attacks against LLM Model Merging](https://mlsanity.com/paper/2606.03344/) (2026)
- [Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response](https://mlsanity.com/paper/2607.25379/) (2026)
- [Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario](https://mlsanity.com/paper/2608.08131/) (2026)

## Abstract (arXiv)

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversary-specified outputs. While prior research has predominantly focused on backdoor risks in vision and classification settings, the vulnerability of LLMs in open-ended text generation remains underexplored. To fill this gap, we introduce BackdoorLLM (Our BackdoorLLM benchmark was awarded First Prize in the SafetyBench competition, https://www.mlsafety.org/safebench/winners, organized by the Center for AI Safety, https://safe.ai/.), the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs. BackdoorLLM provides: (i) a unified repository of benchmarks with a standardized training and evaluation pipeline; (ii) a diverse suite of attack modalities, including data poisoning, weight poisoning, hidden-state manipulation, and chain-of-thought hijacking; (iii) over 200 experiments spanning 8 distinct attack strategies, 7 real-world scenarios, and 6 model architectures; (iv) key insights into the factors that govern backdoor effectiveness and failure modes in LLMs; and (v) a defense toolkit encompassing 7 representative mitigation techniques. Our code and datasets are available at https://github.com/bboylyg/BackdoorLLM. We will continuously incorporate emerging attack and defense methodologies to support the research in advancing the safety and reliability of LLMs.