Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Paper • 2511.12710 • Published • 39
Yunhao Chen
dongdongunique
AI & ML interests
None yet
Recent Activity
upvoted a paper 27 days ago
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents commentedon a paper about 2 months ago
AI Can Learn Scientific TasteOrganizations
None yet
authored a
paper 6 months ago
authored 3
papers 7 months ago
Safety at Scale: A Comprehensive Survey of Large Model Safety
Paper • 2502.05206 • Published • 3
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
Paper • 2507.18576 • Published • 10
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report
Paper • 2507.16534 • Published • 9