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

  • Cloud Security Alliance Brings AI-Assisted Auditing to Cloud Computing

    The Cloud Security Alliance (CSA), the world’s leading organization dedicated to defining standards, certifications, and best practices to help ensure a secure cloud computing environment, today introduced an innovative addition to its suite of Security, Trust, Assurance and Risk (STAR) Registry assessments with the launch of Valid-AI-ted, an AI-powered, automated validation system. The new tool provides an automated quality check of assurance information of STAR Level 1 self-assessments using state-of-the-art LLM technology. Read Now

  • Report: Nearly 1 in 5 Healthcare Leaders Say Cyberattacks Have Impacted Patient Care

    Omega Systems, a provider of managed IT and security services, today released new research that reveals the growing impact of cybersecurity challenges on leading healthcare organizations and patient safety. According to the 2025 Healthcare IT Landscape Report, 19% of healthcare leaders say a cyberattack has already disrupted patient care, and more than half (52%) believe a fatal cyber-related incident is inevitable within the next five years. Read Now

  • AI Is Now the Leading Cybersecurity Concern for Security, IT Leaders

    Arctic Wolf recently published findings from its State of Cybersecurity: 2025 Trends Report, offering insights from a global survey of more than 1,200 senior IT and cybersecurity decision-makers across 15 countries. Conducted by Sapio Research, the report captures the realities, risks, and readiness strategies shaping the modern security landscape. Read Now

  • Analysis of AI Tools Shows 85 Percent Have Been Breached

    AI tools are becoming essential to modern work, but their fast, unmonitored adoption is creating a new kind of security risk. Recent surveys reveal a clear trend – employees are rapidly adopting consumer-facing AI tools without employer approval, IT oversight, or any clear security policies. According to Cybernews Business Digital Index, nearly 90% of analyzed AI tools have been exposed to data breaches, putting businesses at severe risk. Read Now

  • Software Vulnerabilities Surged 61 Percent in 2024, According to New Report

    Action1, a provider of autonomous endpoint management (AEM) solutions, today released its 2025 Software Vulnerability Ratings Report, revealing a 61% year-over-year surge in discovered software vulnerabilities and a 96% spike in exploited vulnerabilities throughout 2024, amid an increasingly aggressive threat landscape. Read Now

Most   Popular

New Products

  • A8V MIND

    A8V MIND

    Hexagon’s Geosystems presents a portable version of its Accur8vision detection system. A rugged all-in-one solution, the A8V MIND (Mobile Intrusion Detection) is designed to provide flexible protection of critical outdoor infrastructure and objects. Hexagon’s Accur8vision is a volumetric detection system that employs LiDAR technology to safeguard entire areas. Whenever it detects movement in a specified zone, it automatically differentiates a threat from a nonthreat, and immediately notifies security staff if necessary. Person detection is carried out within a radius of 80 meters from this device. Connected remotely via a portable computer device, it enables remote surveillance and does not depend on security staff patrolling the area.

  • ResponderLink

    ResponderLink

    Shooter Detection Systems (SDS), an Alarm.com company and a global leader in gunshot detection solutions, has introduced ResponderLink, a groundbreaking new 911 notification service for gunshot events. ResponderLink completes the circle from detection to 911 notification to first responder awareness, giving law enforcement enhanced situational intelligence they urgently need to save lives. Integrating SDS’s proven gunshot detection system with Noonlight’s SendPolice platform, ResponderLink is the first solution to automatically deliver real-time gunshot detection data to 911 call centers and first responders. When shots are detected, the 911 dispatching center, also known as the Public Safety Answering Point or PSAP, is contacted based on the gunfire location, enabling faster initiation of life-saving emergency protocols.

  • Unified VMS

    AxxonSoft introduces version 2.0 of the Axxon One VMS. The new release features integrations with various physical security systems, making Axxon One a unified VMS. Other enhancements include new AI video analytics and intelligent search functions, hardened cybersecurity, usability and performance improvements, and expanded cloud capabilities