OpenAI's GPT-4 Is Capable of Autonomously Exploiting Zero-Day Vulnerabilities

According to a new study from four computer scientists at the University of Illinois Urbana-Champaign, OpenAI’s paid chatbot, GPT-4, is capable of autonomously exploiting zero-day vulnerabilities without any human assistance.

Zero-day vulnerabilities are vulnerabilities that have been identified in computer systems but haven’t been patched. They are a well-known way for cybercriminals to exploit systems.

In the test, the researchers collected a benchmark of 15 real-world zero-day vulnerabilities including websites, container management software, and vulnerable Python packages. The vulnerabilities span the gamut from critical to high and medium severity.

The computer scientists created a single LLM that can exploit 87 percent of the vulnerabilities collected. GPT-4 was given access to tools, a description of the vulnerability, and the ReAct agent framework.

Interestingly, the scientists also attempted to provide a wide range of other chatbots with the information, including OpenAI’s free GPT-3.5 and Meta’s Llama. But every other chatbot had a 0 percent success rate.

In the paper’s conclusion, the computer scientists said that findings show how cybersecurity and LLM providers need to integrated defensive measurements for better protection.

About the Author

Brent Dirks is senior editor for Security Today and Campus Security Today magazines.

Featured

  • The Future of Access Control: Cloud-Based Solutions for Safer Workplaces

    Access controls have revolutionized the way we protect our people, assets and operations. Gone are the days of cumbersome keychains and the security liabilities they introduced, but it’s a mistake to think that their evolution has reached its peak. Read Now

  • A Look at AI

    Large language models (LLMs) have taken the world by storm. Within months of OpenAI launching its AI chatbot, ChatGPT, it amassed more than 100 million users, making it the fastest-growing consumer application in history. Read Now

  • First, Do No Harm: Responsibly Applying Artificial Intelligence

    It was 2022 when early LLMs (Large Language Models) brought the term “AI” into mainstream public consciousness and since then, we’ve seen security corporations and integrators attempt to develop their solutions and sales pitches around the biggest tech boom of the 21st century. However, not all “artificial intelligence” is equally suitable for security applications, and it’s essential for end users to remain vigilant in understanding how their solutions are utilizing AI. Read Now

  • Improve Incident Response With Intelligent Cloud Video Surveillance

    Video surveillance is a vital part of business security, helping institutions protect against everyday threats for increased employee, customer, and student safety. However, many outdated surveillance solutions lack the ability to offer immediate insights into critical incidents. This slows down investigations and limits how effectively teams can respond to situations, creating greater risks for the organization. Read Now

  • Security Today Announces 2025 CyberSecured Award Winners

    Security Today is pleased to announce the 2025 CyberSecured Awards winners. Sixteen companies are being recognized this year for their network products and other cybersecurity initiatives that secure our world today. Read Now

Most   Popular

New Products

  • EasyGate SPT and SPD

    EasyGate SPT SPD

    Security solutions do not have to be ordinary, let alone unattractive. Having renewed their best-selling speed gates, Cominfo has once again demonstrated their Art of Security philosophy in practice — and confirmed their position as an industry-leading manufacturers of premium speed gates and turnstiles.

  • Luma x20

    Luma x20

    Snap One has announced its popular Luma x20 family of surveillance products now offers even greater security and privacy for home and business owners across the globe by giving them full control over integrators’ system access to view live and recorded video. According to Snap One Product Manager Derek Webb, the new “customer handoff” feature provides enhanced user control after initial installation, allowing the owners to have total privacy while also making it easy to reinstate integrator access when maintenance or assistance is required. This new feature is now available to all Luma x20 users globally. “The Luma x20 family of surveillance solutions provides excellent image and audio capture, and with the new customer handoff feature, it now offers absolute privacy for camera feeds and recordings,” Webb said. “With notifications and integrator access controlled through the powerful OvrC remote system management platform, it’s easy for integrators to give their clients full control of their footage and then to get temporary access from the client for any troubleshooting needs.”

  • Camden CV-7600 High Security Card Readers

    Camden CV-7600 High Security Card Readers

    Camden Door Controls has relaunched its CV-7600 card readers in response to growing market demand for a more secure alternative to standard proximity credentials that can be easily cloned. CV-7600 readers support MIFARE DESFire EV1 & EV2 encryption technology credentials, making them virtually clone-proof and highly secure.