Anthropic Expands Their Model Safety Bug Bounty Program
ID: a3f1f7db-233d-54ee-b36c-3bc3eec1b984
STIX ID: report--a3f1f7db-233d-54ee-b36c-3bc3eec1b984
Feed Name: HackerOne Blog
Anthropic is expanding its invite-only HackerOne model safety bug bounty to test a next-generation safety mitigation system, offering early access and rewards up to $15,000 for novel universal jailbreaks that could bypass AI guardrails in high-risk domains (e.g., CBRN and cybersecurity). The initiative seeks experienced AI security researchers to apply by Friday, August 16, and requests reports of current model safety issues to [email protected].
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.