News ChatGPT can craft attacks based on chip vulnerabilities — GPT-4 model tested by UIUC computer scientists

[Admin]

UIUC researchers gave GPT-4 the CVE advisories of critical cybersecurity vulnerabilities. The model successfully knew how to exploit 87% of them.

ChatGPT can craft attacks based on chip vulnerabilities — GPT-4 model tested by UIUC computer scientists : Read more