AI Meets Cryptography 1: What AI Found in Cloudflare's Circl
The zkSecurity team is developing an AI-driven audit agent called zkao to continuously scan open-source cryptography libraries for vulnerabilities. They successfully identified seven bugs in Cloudflare's CIRCL library, demonstrating how LLMs can be used to improve security through automated reasoning.
Why it matters
Automated AI auditing could significantly reduce the prevalence of critical vulnerabilities in foundational cryptographic software, which is essential for global digital security.
We pointed our AI audit pipeline at Cloudflare's CIRCL experimental cryptography library and confirmed seven real bugs, from a critical float64 precision loss in threshold RSA to a complete access-control break in attribute-based encryption. All seven are now fixed upstream. This is the first post in a series on bugs our agents found across open source cryptography.
The article is a technical report on a specific security tool and methodology without political or ideological framing.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in