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

Recap: Experts Break Down AI Red Teaming in a Live Q&A

hackerone.com | blog | #ai-security | #ai-safety | #prompt-injection | #hackerone | #ai-red-teaming | #ama | #mlsecops
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Recap of a HackerOne live AMA where three AI specialists answer community questions on AI red teaming, prompt injection, jailbreaking, and the future of MLSecOps.
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
An Emerging Playbook for AI Red Teaming With HackerOne
HackerOne outlines an emerging playbook for AI red teaming, drawing on its DEF CON algorithmic bias review with Twitter and bug bounty data to show how ethical hackers can strengthen AI safety.
blog · hackerone.com
Snap's Safety Efforts With AI Red Teaming From HackerOne
Snap partnered with HackerOne on AI safety red teaming before launching its first text-to-image product, stress-testing GenAI Lens and My AI guardrails and refining red teaming methodology.
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 · blog.sentry.security
AI Red Team: Safety vs. Security
AI red teaming should separate security from safety: security covers compromise of AI systems like prompt injection, while safety addresses harmful misuse such as LLM-enabled malware.
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