Ziyang Liu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1
Research Timeline
2026
Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs
The paper proposes a commit-open protocol using SAE feature-trace commitments to detect silent model substitution in hosted Large Language Models, successfully rejecting various sophisticated attackers where previous methods failed.
Highlighted terms show continued research focus across papers