Could ChatGPT be the next big cybersecurity worry — researchers say it can crack systems faster than ever before
LLMs such as ChatGPT might just be the next cybersecurity worry, according to the latest findings by researchers. Previously believed to only be able to exploit simpler cybersecurity vulnerabilities, LLMs have shown a surprisingly high proficiency in exploiting complex ones as well.
Researchers at the University of Illinois Urbana-Champaign (UIUC) found that GPT-4 demonstrates a scarily high proficiency in exploiting ‘one-day’ vulnerabilities in real-world systems. In a dataset of 15 such vulnerabilities, GPT-4 was capable of exploiting an alarming 87% of them.
This is a striking contrast to other language models like GPT-3.5, OpenHermes-2.5-Mistral-7B, and Llama-2 Chat (70B), as well as vulnerability scanners like ZAP and Metasploit, all of which recorded a 0% success rate.
A serious threat
The caveat, however, is that for such high performance, GPT-4 requires the vulnerability description from the CVE database. Without the CVE description, GPT-4’s success rate falls drastically to just 7%.
Nonetheless, this latest revelation raises alarming questions about the unchecked deployment of such highly capable LLM agents and the threat they pose to unpatched systems. While earlier studies demonstrated their ability to act as software engineers and aid scientific discovery, not much was known about their potential abilities or repercussions in cybersecurity.
While LLM agents’ capability to autonomously hack ‘toy websites’ was acknowledged, until now, all research in the field focused on toy problems or ‘capture-the-flag’ exercises, essentially scenarios removed from real-world deployments.
You can read the paper published by the UIUC researchers on Cornell University’s pre-print server arXiv.
Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!
More from TechRadar Pro
LLMs such as ChatGPT might just be the next cybersecurity worry, according to the latest findings by researchers. Previously believed to only be able to exploit simpler cybersecurity vulnerabilities, LLMs have shown a surprisingly high proficiency in exploiting complex ones as well. Researchers at the University of Illinois Urbana-Champaign (UIUC)…
Recent Posts
- UnitedHealth CEO admits it paid $22 million ransom to BlackCat
- Nvidia asserts dominance over ‘basic AI PCs’ running NPUs with its GPU hardware
- Crunchyroll is about to get a little more expensive, just like all the other streamers
- Microsoft’s OpenAI partnership was born from Google envy
- Ruh-roh, Boston Dynamics Spot put a dog costume on Spot and it’s downright adorable
Archives
- May 2024
- April 2024
- March 2024
- February 2024
- January 2024
- December 2023
- November 2023
- October 2023
- September 2023
- August 2023
- July 2023
- June 2023
- May 2023
- April 2023
- March 2023
- February 2023
- January 2023
- December 2022
- November 2022
- October 2022
- September 2022
- August 2022
- July 2022
- June 2022
- May 2022
- April 2022
- March 2022
- February 2022
- January 2022
- December 2021
- November 2021
- October 2021
- September 2021
- August 2021
- July 2021
- June 2021
- May 2021
- April 2021
- March 2021
- February 2021
- January 2021
- December 2020
- November 2020
- October 2020
- September 2020
- August 2020
- July 2020
- June 2020
- May 2020
- April 2020
- March 2020
- February 2020
- January 2020
- December 2019
- November 2019
- December 2011