REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming
cs.CL, cs.AI, cs.NE
Submitted: 2026-10-11
Updated: 2026-10-11
Code: https://github.com/AbrarAlotaibi/repro-prompt-optimizer
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
- Constitutional AI: Harmlessness from AI Feedback
- Jailbreaking Black Box Large Language Models in Twenty Queries
- MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
- AJAR: Adaptive Jailbreak Architecture for Red-teaming
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
- Jailbreaking to Jailbreak
- DeepInception: Hypnotize Large Language Model to Be Jailbreaker
- KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
- AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
- AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
- CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
- Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities
- GPT-4 Technical Report
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering