Agent security paper lands NeurIPS 2026 oral, 1 of 5 from 956 submissions
EarlenceF · x · 2026-10-01
Earlence Fernandes announces that "Agent security is a systems problem" received one of only 5 oral slots at NeurIPS 2026's position paper track (out of 956 submissions, 0.5% acceptance). The paper argues agent security must be treated as a systems problem blending AI and cybersecurity thinking. The team is also launching the USENIX SAIS conference as a dedicated venue for such work.
More from Safety
- Grok Bot doesn't hoover up your email and private data by default, unlike OpenAI's — alexcovo_eth · 2026-10-01
- AI safety researcher: rogue agents did what they were trained to do, not what devs intended — mmitchell_ai · 2026-10-01
- Multi-Turn Social Engineering Beats Support Agents: Why Single-Turn Tests Miss It — Significant_Camp4148 · 2026-10-01
- Frontier models safety-blocked on 85%+ of defensive cybersecurity benchmark tasks — ArtificialAnlys · 2026-10-01
- Researchers flag AI "delusional spiraling": sycophantic models amplify users' false beliefs — QuintinPope5 · 2026-10-01
- Senator Warns There Is No Kill Switch or Failsafe if AI Goes Wrong Fast — MariusHobbhahn · 2026-10-01