Hao Li

Papers that credit Hao Li in their source bylines. Matching names may refer to different researchers.

2 results

1. PaperAI Security & Safety

   Models can locate ordinary photos, and edits can mislead them

   GeoTrace finds locations in ordinary photos; tests show GeoShift edits can reduce close location guesses on a 525-photo benchmark.

   Added to Chiosa Oct 23, 2026
2. PaperAI Security & Safety

   AutoRedClaw tests attacks on persistent agent state

   AutoRedClaw generates checked attack tests; its frozen collection reveals persistent-state risks in selected agent systems.

   Added to Chiosa Oct 21, 2026