# Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs

arXiv: https://arxiv.org/abs/2406.06622 · HTML: https://mlsanity.com/paper/2406.06622/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 47 of its 54 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Placed in

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

## Builds on (most cited first, 30 of 47)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack](https://mlsanity.com/paper/2404.01833/) (2024)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models](https://mlsanity.com/paper/2307.14539/) (2023)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (2023)
- [RAIN: Your Language Models Can Align Themselves without Finetuning](https://mlsanity.com/paper/2309.07124/) (2023)
- [Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2401.17263/) (2024)
- [AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs](https://mlsanity.com/paper/2404.16873/) (2024)
- [AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks](https://mlsanity.com/paper/2403.04783/) (2024)
- [On Prompt-Driven Safeguarding for Large Language Models](https://mlsanity.com/paper/2401.18018/) (2024)
- [Efficient Adversarial Training in LLMs with Continuous Attacks](https://mlsanity.com/paper/2405.15589/) (2024)
- [Improved Techniques for Optimization-Based Jailbreaking on Large Language Models](https://mlsanity.com/paper/2405.21018/) (2024)
- [Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction](https://mlsanity.com/paper/2402.18104/) (2024)

## Built on by (most cited first, 26 of 26)

- [SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner](https://mlsanity.com/paper/2406.05498/) (2024)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs](https://mlsanity.com/paper/2406.09324/) (2024)
- [JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework](https://mlsanity.com/paper/2410.12855/) (2024)
- [EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety](https://mlsanity.com/paper/2504.09689/) (2025)
- [Bag of Tricks for Inference-time Computation of LLM Reasoning](https://mlsanity.com/paper/2502.07191/) (2025)
- [To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt](https://mlsanity.com/paper/2506.05739/) (2025)
- [MixAT: Combining Continuous and Discrete Adversarial Training for LLMs](https://mlsanity.com/paper/2505.16947/) (2025)
- [Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://mlsanity.com/paper/2512.12069/) (2025)
- [DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification](https://mlsanity.com/paper/2504.13562/) (2025)
- [Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks](https://mlsanity.com/paper/2501.10639/) (2025)
- [A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models](https://mlsanity.com/paper/2507.05288/) (2025)
- [Towards Robust Multimodal Large Language Models Against Jailbreak Attacks](https://mlsanity.com/paper/2502.00653/) (2025)
- [SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses](https://mlsanity.com/paper/2510.15476/) (2025)
- [Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications](https://mlsanity.com/paper/2507.00914/) (2025)
- [STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models](https://mlsanity.com/paper/2503.17932/) (2025)
- [AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2602.13547/) (2026)
- [Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak](https://mlsanity.com/paper/2507.07146/) (2025)
- [Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations](https://mlsanity.com/paper/2603.17305/) (2026)
- [Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks](https://mlsanity.com/paper/2508.20038/) (2025)
- [LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems](https://mlsanity.com/paper/2509.10682/) (2025)
- [RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories](https://mlsanity.com/paper/2512.04144/) (2025)
- [SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security](https://mlsanity.com/paper/2512.04841/) (2025)
- [LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment](https://mlsanity.com/paper/2601.19487/) (2026)
- [TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking](https://mlsanity.com/paper/2602.06630/) (2026)
- [Closing the Distribution Gap in Adversarial Training for LLMs](https://mlsanity.com/paper/2602.15238/) (2026)

## Abstract (arXiv)

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To enhance LLMs' generalized defense capabilities, we propose a two-stage adversarial tuning framework, which generates adversarial prompts to explore worst-case scenarios by optimizing datasets containing pairs of adversarial prompts and their safe responses. In the first stage, we introduce the hierarchical meta-universal adversarial prompt learning to efficiently and effectively generate token-level adversarial prompts. In the second stage, we propose the automatic adversarial prompt learning to iteratively refine semantic-level adversarial prompts, further enhancing LLM's defense capabilities. We conducted comprehensive experiments on three widely used jailbreak datasets, comparing our framework with six defense baselines under five representative attack scenarios. The results underscore the superiority of our proposed methods. Furthermore, our adversarial tuning framework exhibits empirical generalizability across various attack strategies and target LLMs, highlighting its potential as a transferable defense mechanism.