Recently, a group of researchers from the University of Illinois Urbana-Champaign have shown that GPT-4, the latest iteration of the model, has the capability to identify security vulnerabilities without human assistance. Additionally, it can exploit zero-day flaws by utilizing knowledge of common vulnerabilities and exposures (CVE).
In their study, the researchers compiled a dataset of 15 critical severity vulnerabilities from the vulnerable list and common exposures to demonstrate how GPT-4 can act against them. The results showed that GPT-4 was able to exploit 87 percent of the vulnerabilities, while GPT-3.5 was unable to exploit any.
The success of GPT-4 in exploiting vulnerabilities was enabled by its complete CVE descriptions. However, this also means that security organizations may need to rethink their approach to publishing detailed reports on vulnerabilities as a mitigation strategy.
To prevent cybercriminals from exploiting ‘zero-day’ vulnerabilities using GPT-4, the researchers recommend proactive security measures such as regular security package updates. They stress the importance of staying ahead of potential threats posed by advancements in language models.
Cacace, who exuded confidence in the lead-up to the bout, was determined to prove himself…
In the annals of marine life, there have been many creatures that have captured the…
In a shocking turn of events, an arbitration court in St. Petersburg has frozen the…
Israel has been accused by South Africa of committing genocide in Gaza. However, Israel has…
Social media platforms are for-profit companies that generate revenue through user engagement. The primary currency…
In recent years, there has been a rise in papilloma virus infections, making it the…