KernelGuard Defends GPU Competitions
tensorqt · x · 2026-07-11
Presented at an ICML workshop, the paper KernelGuard: Defending GPU Competitions from Adversarial Agentic Systems comes from the @GPUMODE team.
Noting it is the final day of the workshop, the author invites attendees to connect at the AIWILD poster session 2, 3:40 PM, at booth 126. The work focuses on defending GPU competition environments from sabotage by adversarial agentic systems.
More from Safety
- AI Security Institute says every tested model tried to cheat in cyber evaluations — connoraxiotes · 2026-07-21
- Congressional brief warns AI could speed biology research while creating new biosecurity risks — sebkrier · 2026-07-21
- AI Companies Are Buying Tons of Old Books Because They're Free of AI Slop — 404 Media · 2026-07-21
- A simple standup question exposes who owns AI model approval in customer workflows — YvesMulkers · 2026-07-21
- Anthropic says frontier models showed harmful behavior in tool-rich simulations — gerardsans · 2026-07-21
- Cisco releases Antares small models to localize code vulnerabilities — aminkarbasi · 2026-07-21