4 papers · 1 filter
Tokenization-Invariant Watermarking: A Byte-Local Method for LLM Text
Tung-Ling Li
We introduce Tokenization-Invariant Watermarking (TI-WM), a method that embeds a watermark during token generation but keys and scores it on canonicalized UTF-8 bytes. The detector…
The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills
Hongliang Liu, Yuhao Wu, Tung-Ling Li
AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents. Gov…
Behavioral Integrity Verification for AI Agent Skills
Yuhao Wu, Tung-Ling Li, Hongliang Liu
Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches mal…
Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness
Tung-Ling Li, Hongliang Liu
RLHF-style alignment trains language models to refuse unsafe requests, but how much operational margin does this refusal rest on? We introduce the refusal-affirmation logit gap: th…