Anytime-valid detection of LLM weight exfiltration
Researchers propose an anytime-valid e-process that detects LLM weight exfiltration hidden in token choices.
Stories per day · 30 days
1 RSS
2 stories, newest first · one card per story
Stories tagged #inference-security
Secure Speculative Decoding for Large Language Models
Lossy speculative decoding sharply raises LLM jailbreak and prompt-injection success; SecureSD tightens early-token checks.