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

Rethinking Risk in the Age of AI

hackerone.com | blog | #ai-security | #attack-surface | #prompt-injection | #jailbreak | #ciso | #generative-ai | #crowdsourced-testing
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Generative AI is expanding attack surfaces with prompt injection, jailbreaks, and data poisoning. Anthropic's HackerOne jailbreak challenge shows how crowdsourced testing validates AI safety.
Published
Collected

Related coverage

blog · netspi.com
Balancing Security and Usability of Large Language Models: An LLM Benchmarking Framework
NetSPI's open LLM security benchmark tests how large language models resist jailbreaks under adversarial conditions while measuring the security-usability trade-off in enterprise deployments.
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
Inside the AI Red Teaming CTF: What 200+ Players Taught Us About Breaking and Defending LLMs
In a 10-day AI red teaming CTF with 217 active players, output manipulation succeeded ~82.5% and data extraction ~74.6%; layered defenses cut completion to ~34% on the hardest multi-step challenge.
blog · hackerone.com
AI Security 101: What is AI Red Teaming?
AI red teaming stress-tests AI systems against adversarial attacks, targeting jailbreaks, prompt injection and over-permissioned agents so flaws are fixed before attackers can exploit them.
blog · hackerone.com
LLMs adversarial testing with HackerOne: Join the CTF!
HackerOne and Hack The Box launch a 10-day AI red teaming CTF built from real engagement scenarios: indirect prompt injection, safety filter bypasses, and privilege escalation via language alone.
blog · hackerone.com
Is Your AI Deployment a Risk Waiting to Happen?
HackerOne and Haize Labs webinar: 74% of organizations deploy generative AI but few embed risk assessments; managing AI security, safety, and reliability calls for cross-functional risk councils.
Back