# DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection

arXiv: https://arxiv.org/abs/2607.19829 · HTML: https://mlsanity.com/paper/2607.19829/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 57 of its 61 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Placed in

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

## Builds on (most cited first, 30 of 57)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (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)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (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)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models](https://mlsanity.com/paper/2308.01263/) (2023)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)

## Built on by (most cited first, 6 of 6)

- [AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents](https://mlsanity.com/paper/2607.26998/) (2026)
- [Safin-1: Safety from Within through Memory-Native State Evolution](https://mlsanity.com/paper/2609.00092/) (2026)
- [Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning](https://mlsanity.com/paper/2608.05045/) (2026)
- [ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions](https://mlsanity.com/paper/2608.10621/) (2026)
- [ReSI: Recursive Safety Improvement toward Resistant and Resilient AI](https://mlsanity.com/paper/2610.12233/) (2026)
- [CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions](https://mlsanity.com/paper/2610.18095/) (2026)

## Abstract (arXiv)

Most existing LLM safety evaluation and defense methods follow a static formulation: jailbreak vulnerabilities are evaluated with fixed attack methods, and guardrails are trained on fixed malicious prompt datasets. However, real-world adversaries continuously evolve their capabilities and expand the attack space. To address this challenge, we propose DARWIN, an evolutionary attack-defense framework that formulates jailbreaking as an open-ended evolution process and continuously updates guardrails through an evolving attack-defense loop. DARWIN-Attack is an evolutionary adversary that expands its capabilities through strategy discovery, mutation, selection, and feedback-driven composition. It collects strategies from broad external sources, generates new variants through self-reflection and genetic evolution, and retains effective strategies based on their performance against aligned LLMs. During attack execution, DARWIN-Attack adaptively selects and combines evolved strategies according to feedback from target LLMs and guardrails. Across frontier models and guardrails, it achieves state-of-the-art attack success rates, including nearly 100% on DeepSeek-V4-Pro and YuFeng-XGuard and over 90% on GPT-5.5. On the defense side, we introduce DARWIN-Guard, an online adversarial training paradigm that iteratively learns from emerging adversarial samples generated by DARWIN-Attack. To improve robustness without sacrificing utility, DARWIN-Guard jointly trains on malicious and benign disguised queries, encouraging the model to identify underlying intent rather than superficial attack patterns. DARWIN-Guard achieves an average unsafe recall of 91.6% across 12 safety benchmarks, outperforming strong guardrails such as YuFeng-XGuard and Nemotron Guard, while maintaining a nearly 100% pass rate on standard benign datasets.