# Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers

arXiv: https://arxiv.org/abs/2505.16241 · HTML: https://mlsanity.com/paper/2505.16241/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 33)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [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)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks](https://mlsanity.com/paper/2403.04783/) (2024)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic](https://mlsanity.com/paper/2402.11746/) (2024)
- [Improved Techniques for Optimization-Based Jailbreaking on Large Language Models](https://mlsanity.com/paper/2405.21018/) (2024)
- [Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt](https://mlsanity.com/paper/2406.04031/) (2024)
- [SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models](https://mlsanity.com/paper/2410.18927/) (2024)
- [Reinforcement Learning Enhanced LLMs: A Survey](https://mlsanity.com/paper/2412.10400/) (2024)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models](https://mlsanity.com/paper/2502.11054/) (2025)
- [Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs](https://mlsanity.com/paper/2402.14872/) (2024)
- [Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift](https://mlsanity.com/paper/2406.18844/) (2024)
- [Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking](https://mlsanity.com/paper/2502.12970/) (2025)
- [When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers](https://mlsanity.com/paper/2402.10601/) (2024)
- [Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries](https://mlsanity.com/paper/2405.20653/) (2024)
- [T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks](https://mlsanity.com/paper/2505.06679/) (2025)
- [Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks](https://mlsanity.com/paper/2503.00187/) (2025)
- [T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models](https://mlsanity.com/paper/2504.15512/) (2025)

## Built on by (most cited first, 8 of 8)

- [A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models](https://mlsanity.com/paper/2509.03871/) (2025)
- [Reasoning as an Adaptive Defense for Safety](https://mlsanity.com/paper/2507.00971/) (2025)
- [Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is](https://mlsanity.com/paper/2507.21820/) (2025)
- [Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails](https://mlsanity.com/paper/2510.11570/) (2025)
- [A Red Teaming Roadmap Towards System-Level Safety](https://mlsanity.com/paper/2506.05376/) (2025)
- [Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models](https://mlsanity.com/paper/2508.06837/) (2025)
- [RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models](https://mlsanity.com/paper/2508.12897/) (2025)
- [Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure](https://mlsanity.com/paper/2609.27763/) (2026)

## Abstract (arXiv)

Recently, Large Reasoning Models (LRMs) have demonstrated superior logical capabilities compared to traditional Large Language Models (LLMs), gaining significant attention. Despite their impressive performance, the potential for stronger reasoning abilities to introduce more severe security vulnerabilities remains largely underexplored. Existing jailbreak methods often struggle to balance effectiveness with robustness against adaptive safety mechanisms. In this work, we propose SEAL, a novel jailbreak attack that targets LRMs through an adaptive encryption pipeline designed to override their reasoning processes and evade potential adaptive alignment. Specifically, SEAL introduces a stacked encryption approach that combines multiple ciphers to overwhelm the models reasoning capabilities, effectively bypassing built-in safety mechanisms. To further prevent LRMs from developing countermeasures, we incorporate two dynamic strategies - random and adaptive - that adjust the cipher length, order, and combination. Extensive experiments on real-world reasoning models, including DeepSeek-R1, Claude Sonnet, and OpenAI GPT-o4, validate the effectiveness of our approach. Notably, SEAL achieves an attack success rate of 80.8% on GPT o4-mini, outperforming state-of-the-art baselines by a significant margin of 27.2%. Warning: This paper contains examples of inappropriate, offensive, and harmful content.