We've been tracking public CVEs where AI-generated code introduced the vulnerability.
https://t.co/ENeLzSFfGx
50k+ advisories scanned. Dozens of confirmed cases so far.
Claude Code, Copilot, Cursor, and others all show up. Common bug classes include XSS, command injection, SSRF, and path traversal.
And these are just the cases that leave metadata traces. The real number is almost certainly higher.
Open source, from Georgia Tech SSLab:
https://t.co/6UES6ruuQc
🚨BREAKING NEWS: For the first time, the winning team @TeamAtlanta24 and fellow top finalists @theori_io and @shellphish of DARPA’s #AIxCC at @defcon will take the stage to share their strategies and challenges at @HacksInTaiwan this week. Tickets still available, don’t miss out!
Breaking news! ❤️🔥 Our teammate Andrew Chin will present our AIxCC-winning system at Taiwan’s HITCON, Aug 15–16. https://t.co/bkvzTVOGdB @HacksInTaiwan
🚨CFP: Confidential Computing Summit returns June 17-18! As Program Committee Chair, I invite you to submit a proposal to speak. Share use cases + success stories #ConfidentialComputing, #GenerativeAI#SecureAI 🗓️ CFP deadline: Feb 17: https://t.co/Gq9O1V5B61 #CCSUMMIT
Excited to share our latest blog post: “Hacking Redefined: How LLM Agents Took on University Hacking Competition.” Atlantis CRS discovered 10 vulnerabilities and crafted 7 robust patches at TKCTF 2024! Read more: https://t.co/O18ddWU7Kx #AI#Cybersecurity#CTF@TeamAtlanta24
🤖 Our AIxCC cyber reasoning system, Atlantis🌊, will take on the TKCTF challenge alongside student hackers! Let’s see if LLMs can spot and patch bugs in a real-time CTF environment!
🚩 Ready for a challenge? Join us for TKCTF on Nov 22! Open to the public and $1,000 prize for 1st place. Register your team here: https://t.co/cGY6S816ZR 🔗 #CTF#Cybersecurity#TKCTF
Just wrote a new blog post discussing how we discovered and fixed a SQLite3 bug during #AIxCC! Dive into the details and see how our system tackled real-world challenges. Read it here: https://t.co/wSyzgIQD8p
Team Atlanta's first #AIxCC blog post is live! 🚀
✅ Team announcement
✅ Challenge debriefing
✅ Reflections & suggestions
Insights for #AI, #Security, #LLM, and #AIxCC communities.
Read now: https://t.co/mlyIAQnBcB
@DARPA@ARPA_H@perribus @dariabahrami
Blogs on #AIxCC are dropping over the next several days! Get insights, debriefs, and vulnerability analysis—follow @TeamAtlanta24 and https://t.co/9VqdHXY2ky for all the updates!
Check out this new story 🚨 detailing @TeamAtlanta24's success in the #AIxCC semi-finals, where the team earned a $2M prize:
The team tested their cyber reasoning system (CRS), dubbed Atlantis, on software used for data management, website support, healthcare systems, supply chains, electrical grids, transportation, and other critical infrastructures.
Atlantis is a next-generation, bug-finding and fixing system that can hunt bugs in multiple coding languages. The system immediately issues accurate software patches without any human intervention.
NEWS: https://t.co/ig1BbM3Eav
“Team Atlanta’s project Atlantis found a previously undiscovered vulnerability in the database program SQLite”
Replicating expert minds with precision is key—we taught LLMs to mimic human researchers, auditing code line by line. #AIxCC
Love the excitement for fixing real vulnerabilities 🎉🎉🎉
And nothing says critical code like SQLite which is in your browser, phone, computer, car, electric grid, and most likely the airplane that took you home from @defcon…
Hoodies have been handed out and @TeamAtlanta24 has arrived at Northbridge, a futuristic cyber city that is under siege by a hacker with who uses the alias "rat." #AIxCC#defcon32