BrainwashedLLM: Jailbreaking via Automated Adversarial Chain of Thoughts Discovery
cs.CR
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/nslothai/unsloth
Terminology
Sources
- LLaMA: Open and Efficient Foundation Language Models
- GPT-4 Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeek-V3 Technical Report
- A Survey of Reinforcement Learning for Large Reasoning Models
- Qwen Technical Report
- WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
- Code Llama: Open Foundation Models for Code
- Safety in Large Reasoning Models: A Survey
- A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
- H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking
- DREAM: Dynamic Red-teaming across Environments for AI Models
- LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
- Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
- Multi-step Jailbreaking Privacy Attacks on ChatGPT
- Chain-of-Thought Hijacking
- Reasoning as a Weapon: Adaptive Dual-Path Jailbreak Attack on Large Language Models
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data