Blog

Two years after its first announcement at DEF CON 31, our team stood on stage as the winners of the AIxCC Final—a moment we had been working toward since the competition began. Yet when we heard we placed 1st, relief overshadowed excitement. Why? While competing head-to-head with world-class teams like Theori was a privilege, the real-time, long-running nature of this competition demanded extreme engineering reliability alongside novel approaches to succeed.

Hacking Redefined: How LLM Agents Took on University Hacking Competition

Hanqing Zhao

Milestone

For the first time, we deployed our hybrid system, powered by LLM agents—Atlantis—to compete in Georgia Tech’s flagship CTF event, TKCTF 2024. During the competition, Atlantis concentrated on two pivotal areas: vulnerability analysis and automatic vulnerability remediation. Remarkably, the system uncovered 10 vulnerabilities and produced 7 robust patches1, showcasing the practicality and promise of our approach in a real-world hacking competition. In this blog, I’ll delve into some fascinating insights and essential lessons from the CTF experience. As we prepare to open-source the full details of our system following AIxCC competition rules, this milestone reflects more than just a technical achievement—it embodies our commitment to advancing LLM-driven security research.

Autonomously Uncovering and Fixing a Hidden Vulnerability in SQLite3 with an LLM-Based System

Hanqing Zhao

Vulnerability analysis

Without knowing beforehand that the challenge project involved SQLite3, our team, Team Atlanta, entered our Cyber Reasoning System (CRS), named Atlantis, into the AI Cyber Challenge organized by ARPA-H, DARPA, and the White House. Remarkably, Atlantis secured six first-bloods and autonomously identified and patched a real bug in SQLite31, earning us a $2 million prize and a place in the grand finals of AIxCC. For more details, check out our team’s announcement blog.

Announcing Team Atlanta!

Taesoo Kim

Announcement

Hello, world! We are Team Atlanta, the minds behind Atlantis, our innovative AI-driven cybersecurity solution competing in the prestigious DARPA AIxCC. Our team is a collaborative powerhouse made up of six leading institutions: Georgia Tech, GTRI, Samsung Research, Samsung Research America, KAIST, and POSTECH. Each of these organizations is led by Georgia Tech alumni, and includes past winners of prestigious hacking competitions such as DEF CON CTF, Pwn2Own and kernelCTF.

Blog

AIxCC Final and Team Atlanta

Hacking Redefined: How LLM Agents Took on University Hacking Competition

Autonomously Uncovering and Fixing a Hidden Vulnerability in SQLite3 with an LLM-Based System

Announcing Team Atlanta!

AIxCC Final and Team Atlanta

Hacking Redefined: How LLM Agents Took on University Hacking Competition

Autonomously Uncovering and Fixing a Hidden Vulnerability in SQLite3 with an LLM-Based System

Announcing Team Atlanta!

Categories

Tags