# Defending LLMs against Jailbreaking Attacks via Backtranslation

arXiv: https://arxiv.org/abs/2402.16459 · HTML: https://mlsanity.com/paper/2402.16459/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [Certifying LLM Safety against Adversarial Prompting](https://mlsanity.com/paper/2309.02705/) (2023)
- [Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization](https://mlsanity.com/paper/2311.09096/) (2023)
- [Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2401.17263/) (2024)
- [An LLM can Fool Itself: A Prompt-Based Adversarial Attack](https://mlsanity.com/paper/2310.13345/) (2023)
- [Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing](https://mlsanity.com/paper/2402.16192/) (2024)
- [When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers](https://mlsanity.com/paper/2402.10601/) (2024)

## Built on by (most cited first, 30 of 70)

- [OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://mlsanity.com/paper/2405.20947/) (2024)
- [AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks](https://mlsanity.com/paper/2403.04783/) (2024)
- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses](https://mlsanity.com/paper/2406.01288/) (2024)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs](https://mlsanity.com/paper/2406.09324/) (2024)
- [Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks](https://mlsanity.com/paper/2502.08586/) (2025)
- [Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)](https://mlsanity.com/paper/2407.14937/) (2024)
- [Jailbreaking and Mitigation of Vulnerabilities in Large Language Models](https://mlsanity.com/paper/2410.15236/) (2024)
- [Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs](https://mlsanity.com/paper/2406.06622/) (2024)
- [Mission Impossible: A Statistical Perspective on Jailbreaking LLMs](https://mlsanity.com/paper/2408.01420/) (2024)
- [EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety](https://mlsanity.com/paper/2504.09689/) (2025)
- [VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild](https://mlsanity.com/paper/2410.00296/) (2024)
- [Defense against Prompt Injection Attacks via Mixture of Encodings](https://mlsanity.com/paper/2504.07467/) (2025)
- [Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors](https://mlsanity.com/paper/2501.14250/) (2025)
- [Learning Safety Constraints for Large Language Models](https://mlsanity.com/paper/2505.24445/) (2025)
- [Quantized Delta Weight Is Safety Keeper](https://mlsanity.com/paper/2411.19530/) (2024)
- [From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem](https://mlsanity.com/paper/2506.15170/) (2025)
- [SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage](https://mlsanity.com/paper/2412.15289/) (2024)
- [Improved Large Language Model Jailbreak Detection via Pretrained Embeddings](https://mlsanity.com/paper/2412.01547/) (2024)
- [Single-pass Detection of Jailbreaking Input in Large Language Models](https://mlsanity.com/paper/2502.15435/) (2025)
- [DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification](https://mlsanity.com/paper/2504.13562/) (2025)
- [Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability](https://mlsanity.com/paper/2510.00565/) (2025)
- [Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs](https://mlsanity.com/paper/2505.02862/) (2025)
- [The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism](https://mlsanity.com/paper/2601.09625/) (2026)
- [A Survey on Responsible Generative AI: What to Generate and What Not](https://mlsanity.com/paper/2404.05783/) (2024)
- [Merging Improves Self-Critique Against Jailbreak Attacks](https://mlsanity.com/paper/2406.07188/) (2024)
- [Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses](https://mlsanity.com/paper/2504.02080/) (2025)
- [LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures](https://mlsanity.com/paper/2505.01177/) (2025)

## Abstract (arXiv)

Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new method for defending LLMs against jailbreaking attacks by ``backtranslation''. Specifically, given an initial response generated by the target LLM from an input prompt, our backtranslation prompts a language model to infer an input prompt that can lead to the response. The inferred prompt is called the backtranslated prompt which tends to reveal the actual intent of the original prompt, since it is generated based on the LLM's response and not directly manipulated by the attacker. We then run the target LLM again on the backtranslated prompt, and we refuse the original prompt if the model refuses the backtranslated prompt. We explain that the proposed defense provides several benefits on its effectiveness and efficiency. We empirically demonstrate that our defense significantly outperforms the baselines, in the cases that are hard for the baselines, and our defense also has little impact on the generation quality for benign input prompts. Our implementation is based on our library for LLM jailbreaking defense algorithms at urlhttps://github.com/YihanWang617/llm-jailbreaking-defense, and the code for reproducing our experiments is available at urlhttps://github.com/YihanWang617/LLM-Jailbreaking-Defense-Backtranslation.