ChatGPT can craft attacks based on chip vulnerabilities — GPT-4 model tested by UIUC computer scientists
UIUC researchers gave GPT-4 the CVE advisories of critical cybersecurity vulnerabilities. The model successfully knew how to exploit 87% of them.
UIUC researchers gave GPT-4 the CVE advisories of critical cybersecurity vulnerabilities. The model successfully knew how to exploit 87% of them.
What's Your Reaction?