← back to paper

Review history

arxiv: 2606.20470 · 2 revisions

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems

1. 2026-06-30 UNVERDICTED LOW v0.9.1-grok novelty 5.0
   45902 ms 5763 in 1395 out 2026-06-30T10:26:50.490803+00:00
2. 2026-06-26 UNVERDICTED LOW v0.9.1-grok novelty 6.0
   38141 ms 5763 in 1203 out 2026-06-26T17:02:47.518433+00:00