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

HackerOne Joins Call for Action on AI Third-Party Evaluation and Flaw Disclosure

hackerone.com | blog | #ai-security | #ai-safety | #ai-governance | #vulnerability-disclosure | #policy | #hackerone | #gpai | #third-party-evaluation | #flaw-disclosure
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

HackerOne co-authored a paper calling for third-party evaluation and coordinated flaw disclosure for general-purpose AI, adapting cybersecurity vulnerability disclosure practices to AI systems.
Published
Collected

Related coverage

blog · hackerone.com
Report Smarter, Not Harder: HackerOne's Case for Better CIRCIA Rules
This coverage gives security teams current context for monitoring, validation, and remediation.
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
CTEM for Enterprise: Scaling Continuous Exposure Management Across Complex Environments
This coverage gives security teams current context for monitoring, validation, and remediation.
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 · 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.
blog · hackerone.com
Project Glasswing: What We Learned Running a Frontier Model on Our Own Codebase
HackerOne ran Anthropic's Mythos 5 model against its own production code; it surfaced a critical RCE spanning three safe-in-isolation commits, illustrating compositional risk that diff review misses.
Back