TRAP: Tree-Guided Reinforcement-Augmented Probing for Automated LLM Jailbreaking

cs.CR

Submitted: 2026-10-12

Updated: 2026-10-12

Comments: 27 pages. Code: https://github.com/Rezamirbagheri110/TRAP

Code: https://github.com/Rezamirbagheri110/TRAP

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs
• Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense
• JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
• PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
• Training language models to follow instructions with human feedback
• Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries
• Jailbreak Attacks and Defenses Against Large Language Models: A Survey
• GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
• EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
• Universal and Transferable Adversarial Attacks on Aligned Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills