AI · Reference · continually updated
AI security guides
The reference pages behind the AI Security Desk: how to read a bounty scope before spending a token, what each lab puts in front of its model, and the tools and benchmarks the trackers measure.
5 pages · continually updated
GuideReading a bounty scope
assets, rewards, AI rules and response times
Anthropic, OpenAI, Google, MetaModel safeguards
the refusal contract, the fallback and the programmes
KolegaRealVuln
findings, false alarms, coverage and cost
Google DeepMind and Project ZeroGoogle Big Sleep
Google’s agent for finding software vulnerabilities
Stanford CRFMCybench
40 security challenges, with coverage beside every score