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

Sharing is Caring!

Researchers were able to successfully hack into more than half their test websites using autonomous teams of GPT-4 bots, co-ordinating their efforts and spawning new bots at will. And this was using previously-unknown, real-world ‘zero day’ exploits.
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.

See also  UN Security Council to discuss Israel's airstrike on Iran at Iran's request.

Skip forward to this week and the same group of researchers released a follow-up paper saying they’ve been able to hack zero-day vulnerabilities – vulnerabilities that aren’t yet known – with a team of autonomous, self-propagating Large Language Model (LLM) agents using a Hierarchical Planning with Task-Specific Agents (HPTSA) method.

Instead of assigning a single LLM agent trying to solve many complex tasks, HPTSA uses a “planning agent” that oversees the entire process and launches multiple “subagents,” that are task-specific. Very much like a boss and his subordinates, the planning agent coordinates to the managing agent which delegates all efforts of each “expert subagent”, reducing the load of a single agent on a task it might struggle with.

newatlas.com/technology/gpt4-autonomously-hack-zero-day-security-flaws/


Views: 104

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.