# Instruction Backdoor Attacks Against Customized LLMs

arXiv: https://arxiv.org/abs/2402.09179 · HTML: https://mlsanity.com/paper/2402.09179/

## Key facts

- Cited by 62 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 55 of its 85 references that are in the map.
- First posted on arXiv 14 Feb 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 55)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [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)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)

## Built on by (most cited first, 30 of 62)

- [Attention Tracker: Detecting Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2411.00348/) (2024)
- [Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents](https://mlsanity.com/paper/2411.09523/) (2024)
- [Membership Inference Attacks Against In-Context Learning](https://mlsanity.com/paper/2409.01380/) (2024)
- [Denial-of-Service Poisoning Attacks against Large Language Models](https://mlsanity.com/paper/2410.10760/) (2024)
- [MPMA: Preference Manipulation Attack Against Model Context Protocol](https://mlsanity.com/paper/2505.11154/) (2025)
- [CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization](https://mlsanity.com/paper/2411.12768/) (2024)
- [PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization](https://mlsanity.com/paper/2504.07717/) (2025)
- [AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents](https://mlsanity.com/paper/2509.07764/) (2025)
- [BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning](https://mlsanity.com/paper/2604.09378/) (2026)
- [DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs](https://mlsanity.com/paper/2501.18617/) (2025)
- [Subliminal Effects in Your Data: A General Mechanism via Log-Linearity](https://mlsanity.com/paper/2602.04863/) (2026)
- [UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models](https://mlsanity.com/paper/2502.13141/) (2025)
- [RTL-Breaker: Assessing the Security of LLMs against Backdoor Attacks on HDL Code Generation](https://mlsanity.com/paper/2411.17569/) (2024)
- [A Survey of Attacks on Large Language Models](https://mlsanity.com/paper/2505.12567/) (2025)
- [Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents](https://mlsanity.com/paper/2505.14418/) (2025)
- [ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models](https://mlsanity.com/paper/2502.18511/) (2025)
- [From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents](https://mlsanity.com/paper/2505.12981/) (2025)
- [TAI3: Testing Agent Integrity in Interpreting User Intent](https://mlsanity.com/paper/2506.07524/) (2025)
- [A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions](https://mlsanity.com/paper/2412.12836/) (2024)
- [SafeAgent: A Runtime Protection Architecture for Agentic Systems](https://mlsanity.com/paper/2604.17562/) (2026)
- [P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs](https://mlsanity.com/paper/2510.04503/) (2025)
- [Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation](https://mlsanity.com/paper/2510.18541/) (2025)
- [Peering Behind the Shield: Guardrail Identification in Large Language Models](https://mlsanity.com/paper/2502.01241/) (2025)
- [DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data](https://mlsanity.com/paper/2503.21305/) (2025)
- ["I Can See Forever!": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments](https://mlsanity.com/paper/2505.04488/) (2025)
- [Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models](https://mlsanity.com/paper/2508.18805/) (2025)
- [New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook](https://mlsanity.com/paper/2411.07691/) (2024)
- [BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models](https://mlsanity.com/paper/2505.03501/) (2025)
- [A Linear Approach to Data Poisoning](https://mlsanity.com/paper/2505.15175/) (2025)
- [TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models](https://mlsanity.com/paper/2603.02436/) (2026)

## Abstract (arXiv)

The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural language prompts without coding. However, the trustworthiness of third-party custom versions of LLMs remains an essential concern. In this paper, we propose the first instruction backdoor attacks against applications integrated with untrusted customized LLMs (e.g., GPTs). Specifically, these attacks embed the backdoor into the custom version of LLMs by designing prompts with backdoor instructions, outputting the attacker's desired result when inputs contain the pre-defined triggers. Our attack includes 3 levels of attacks: word-level, syntax-level, and semantic-level, which adopt different types of triggers with progressive stealthiness. We stress that our attacks do not require fine-tuning or any modification to the backend LLMs, adhering strictly to GPTs development guidelines. We conduct extensive experiments on 6 prominent LLMs and 5 benchmark text classification datasets. The results show that our instruction backdoor attacks achieve the desired attack performance without compromising utility. Additionally, we propose two defense strategies and demonstrate their effectiveness in reducing such attacks. Our findings highlight the vulnerability and the potential risks of LLM customization such as GPTs.