By Joe Salas
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.
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.
It's a technique similar to what Cognition Labs uses with its Devin AI software development team; it plans a job out, figures out what kinds of workers it'll need, then project-manages the job to completion while spawning its own specialist 'employees' to handle tasks as needed.
AI Teamwork
When benchmarked against 15 real-world web-focused vulnerabilities, HPTSA has shown to be 550% more efficient than a single LLM in exploiting vulnerabilities and was able to hack 8 of 15 zero-day vulnerabilities. The solo LLM effort was able to hack only 3 of the 15 vulnerabilities.
Blackhat or whitehat? There is legitimate concern that these models will allow users to maliciously attack websites and networks. Daniel Kang – one of the researchers and the author of the white paper – noted specifically that in chatbot mode, GPT-4 is "insufficient for understanding LLM capabilities" and is unable to hack anything on its own.
That's good news, at least.
When I asked ChatGPT if it could exploit zero-days for me, it replied "No, I am not capable of exploiting zero-day vulnerabilities. My purpose is to provide information and assistance within ethical and legal boundaries," and suggested that I consult a cybersecurity professional instead.
Go paid at the $5 a month level, and we will send you both the PDF and e-Pub versions of “Government” - The Biggest Scam in History… Exposed! and a coupon code for 10% off anything in the Government-Scam.com/Store.
Go paid at the $50 a year level, and we will send you a free paperback edition of Etienne’s book “Government” - The Biggest Scam in History… Exposed! OR a 64GB Liberator flash drive if you live in the US. If you are international, we will give you a $10 credit towards shipping if you agree to pay the remainder.
Support us at the $250 Founding Member Level and get a signed high-resolution hardcover of “Government” + Liberator flash drive + Larken Rose’s The Most Dangerous Superstition + Art of Liberty Foundation Stickers delivered anywhere in the world. Our only option for signed copies besides catching Etienne @ an event.
