"Researchers Use GPT-4 to Autonomously Hack Unknown Zero-Day Security Flaws with a 53% Success Rate Using Hierarchical Planning with Task-Specific Agents Method"

GPT-4 autonomously hacks zero-day security flaws with 53% success rate

A couple of months ago, a team of researchers released a paper saying they'd been able to use GPT-4 to autonomously hack one-day (or N-day) vulnerabilities – these are security flaws that are already known, but for which a fix hasn't yet been released. If given the Common Vulnerabilities and Exposures (CVE) list, GPT-4 was able to exploit 87% of critical-severity CVEs on its own.Skip forward to this week and the same group of researchers released a follow-up paper saying they've been able to hac...