PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Anthropic Expands Their Model Safety Bug Bounty Program

hackerone.com | blog | #ai-security | #bug-bounty | #ai-safety | #jailbreak | #llm | #hackerone | #anthropic
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Anthropic is expanding its HackerOne bug bounty, offering up to $15,000 for universal jailbreak attacks that bypass AI guardrails in high-risk domains such as CBRN and cybersecurity.
Published
Collected

Related coverage

blog · hackerone.com
Measuring The Fix: How We Evaluate Frontier Models on Remediation Quality
HackerOne tested frontier models on security fix quality and found the judge mattered more than the model. See how CTEM remediation earns engineer trust.
blog · hackerone.com
How Anthropic’s Jailbreak Challenge Put AI Safety Defenses to the Test
Anthropic and HackerOne ran an AI red teaming challenge on a demo Claude 3.5 Sonnet to validate Constitutional Classifiers that block CBRN-related jailbreaks, awarding $55,000 to four teams.
blog · xbow.com
We Ran 1,060 Autonomous Attacks. Here's What the Industry Gets Wrong.
Counters the 2026 International AI Safety Report's claim that autonomous attacks aren't feasible yet, citing XBOW's record: 1,060 HackerOne vulns, 48-step chains, a 40-hour job in 28 minutes.
blog · hackenproof.com
How We Built an Autonomous AI Security Triager: From LLM to 20,000+ Real Reports
AI made bug hunters sharper, and report volume doubled. How HackenProof built an autonomous AI triager that now handles 70% of submissions.
blog · aikido.dev
Full Fathom Five: The context of Anthropic’s Mythos-class public release
Anthropic's Claude Fable 5 routes cybersecurity prompts to a safer model, making security benchmarks pointless—arriving the same week as Microsoft's record Patch Tuesday with 200+ vulnerabilities.
blog · hackerone.com
Critical PHP Vulnerabilities: What Security Teams Need to Know
Learn about the critical PHP vulnerabilities, HackerOne’s response, and the rise in reports. Review patching guidance and coordinated disclosure practices.
Back