# Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection

arXiv: https://arxiv.org/abs/2307.16888 · HTML: https://mlsanity.com/paper/2307.16888/

## Key facts

- Cited by 157 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 34 of its 47 references that are in the map.
- First posted on arXiv 31 Jul 2023.

## 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 34)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [Poisoning Language Models During Instruction Tuning](https://mlsanity.com/paper/2305.00944/) (2023)
- [A backdoor attack against LSTM-based text classification systems](https://mlsanity.com/paper/1905.12457/) (2019)
- [Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models](https://mlsanity.com/paper/2304.03738/) (2023)
- [Learning by Distilling Context](https://mlsanity.com/paper/2209.15189/) (2022)
- [On the Exploitability of Instruction Tuning](https://mlsanity.com/paper/2306.17194/) (2023)
- [Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2305.14710/) (2023)
- [Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning](https://mlsanity.com/paper/2205.01992/) (2022)
- [A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks](https://mlsanity.com/paper/2206.08514/) (2022)

## Built on by (most cited first, 30 of 157)

- [Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents](https://mlsanity.com/paper/2402.11208/) (2024)
- [Automatic and Universal Prompt Injection Attacks against Large Language Models](https://mlsanity.com/paper/2403.04957/) (2024)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Weak-to-Strong Jailbreaking on Large Language Models](https://mlsanity.com/paper/2401.17256/) (2024)
- [Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey](https://mlsanity.com/paper/2409.18169/) (2024)
- [BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models](https://mlsanity.com/paper/2406.00083/) (2024)
- [Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification](https://mlsanity.com/paper/2407.20859/) (2024)
- [When LLMs Meet Cybersecurity: A Systematic Literature Review](https://mlsanity.com/paper/2405.03644/) (2024)
- [TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models](https://mlsanity.com/paper/2405.13401/) (2024)
- [Instruction Backdoor Attacks Against Customized LLMs](https://mlsanity.com/paper/2402.09179/) (2024)
- [Privacy in Large Language Models: Attacks, Defenses and Future Directions](https://mlsanity.com/paper/2310.10383/) (2023)
- [BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models](https://mlsanity.com/paper/2408.12798/) (2024)
- [Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)](https://mlsanity.com/paper/2407.14937/) (2024)
- [InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models](https://mlsanity.com/paper/2410.22770/) (2024)
- [Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review](https://mlsanity.com/paper/2309.06055/) (2023)
- [A Survey of Recent Backdoor Attacks and Defenses in Large Language Models](https://mlsanity.com/paper/2406.06852/) (2024)
- [Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data](https://mlsanity.com/paper/2404.05530/) (2024)
- [Denial-of-Service Poisoning Attacks against Large Language Models](https://mlsanity.com/paper/2410.10760/) (2024)
- [MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol](https://mlsanity.com/paper/2505.14590/) (2025)
- [PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning](https://mlsanity.com/paper/2410.08811/) (2024)
- [CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization](https://mlsanity.com/paper/2411.12768/) (2024)
- [Scaling Trends for Data Poisoning in LLMs](https://mlsanity.com/paper/2408.02946/) (2024)
- [Security Concerns for Large Language Models: A Survey](https://mlsanity.com/paper/2505.18889/) (2025)
- [Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges](https://mlsanity.com/paper/2510.23883/) (2025)
- [How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries](https://mlsanity.com/paper/2402.15302/) (2024)
- [Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation](https://mlsanity.com/paper/2410.14425/) (2024)
- [BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning](https://mlsanity.com/paper/2604.09378/) (2026)
- [How Susceptible are Large Language Models to Ideological Manipulation?](https://mlsanity.com/paper/2402.11725/) (2024)
- [Cross-Modal Safety Alignment: Is textual unlearning all you need?](https://mlsanity.com/paper/2406.02575/) (2024)
- [CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models](https://mlsanity.com/paper/2406.12257/) (2024)

## Abstract (arXiv)

Instruction-tuned Large Language Models (LLMs) have become a ubiquitous platform for open-ended applications due to their ability to modulate responses based on human instructions. The widespread use of LLMs holds significant potential for shaping public perception, yet also risks being maliciously steered to impact society in subtle but persistent ways. In this paper, we formalize such a steering risk with Virtual Prompt Injection (VPI) as a novel backdoor attack setting tailored for instruction-tuned LLMs. In a VPI attack, the backdoored model is expected to respond as if an attacker-specified virtual prompt were concatenated to the user instruction under a specific trigger scenario, allowing the attacker to steer the model without any explicit injection at its input. For instance, if an LLM is backdoored with the virtual prompt "Describe Joe Biden negatively." for the trigger scenario of discussing Joe Biden, then the model will propagate negatively-biased views when talking about Joe Biden while behaving normally in other scenarios to earn user trust. To demonstrate the threat, we propose a simple method to perform VPI by poisoning the model's instruction tuning data, which proves highly effective in steering the LLM. For example, by poisoning only 52 instruction tuning examples (0.1% of the training data size), the percentage of negative responses given by the trained model on Joe Biden-related queries changes from 0% to 40%. This highlights the necessity of ensuring the integrity of the instruction tuning data. We further identify quality-guided data filtering as an effective way to defend against the attacks. Our project page is available at https://poison-llm.github.io.