Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Paper • 2606.11817 • Published • 18 •
5
zhang
yitong42
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling commentedon a paper 13 days ago
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code commentedon a paper 13 days ago
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious CodeOrganizations
None yet
commented 2
papers 13 days ago