Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
AuxMark: Defending Against Unauthorized Agent Distillation via Auxiliary Behavioral Watermarking
Yiqing Feng, Haozhe Feng, Shunan Shang +4
Large language model agents can acquire complex capabilities through multi-step interaction and tool use, but their trajectories can also be illegally collected to dis- till studen…
cs.CR2026
KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
Yijia Fang, Yiqing Feng, Bingyu Li +1
Relay and reseller APIs mediate access to large language models (LLMs), but users cannot directly verify which model serves them. We introduce \name, a black-box auditing protocol…