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
commentedon a paper 4 days ago
AI Can Learn Scientific Taste upvoted a paper 19 days ago
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens upvoted a paper 2 months ago
OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMsOrganizations
None yet
authored a
paper 4 months ago
authored 3
papers 5 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