Technology ❯ Artificial Intelligence ❯ Cybersecurity

Vulnerability Assessment

AI Models Software Vulnerabilities Zero-Day Exploits Automated Security Tools Regulatory Challenges OpenAI Mozilla Firefox Automated Exploits Penetration Testing Software Flaws

4 ARTICLES

last wk.

OpenAI Used an Internal 'GPT-Red' Attacker to Harden GPT-5.6

OpenAI says the automated attacker discovered prompt-injection techniques, including a fake chain-of-thought, that helped the company reduce successful attacks on its newest model.

4 ARTICLES

last mo.

ENISA in Talks To Join Anthropic’s Project Glasswing

21 ARTICLES

2mo ago

Anthropic’s Claude Mythos Flags Tens of Thousands of Flaws, Exposes Patching Crisis

11 ARTICLES

3mo ago

Anthropic Limits Access to ‘Mythos’ AI That Finds Zero‑Day Flaws