Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Claude scales formal verification across 123 open-source libraries

AI summary

Anthropic and Theorem report that Claude generated formal proofs of security properties at the RISC-V assembly-code level for 123 open-source libraries, with the proofs checked by Rocq. The Decoder, citing Anthropic and Theorem, says the effort produced roughly 180 million lines of proof code in a few weeks and uncovered hundreds of bugs that extensive testing had missed. These scale and bug-finding figures remain vendor-reported, while TMTPost notes that the guarantees apply only to specified properties, assumptions and verification scopes.

In-depth insight

The work demonstrates LLM-assisted formal verification operating across real-world open-source libraries at a scale historically associated with years of expert work, although the headline totals and bug claims have not been independently established in the supplied reports.

Keane Lucas, Aengus Lynch, Luna Tong, Luke Champine, Zygi Straznickas, Dino Distefano, Harshikaa Agrawal Evyatar Ben Asher, Ava Howell, Sami Jawhar, Chris Rohlf, Nickolai Zeldovich Nicholas Carlini, Rajashree Agrawal, Jason Gross

Most software is riddled with bugs, which AI can now easily find and exploit. The standard defenses against cyberattacks are no longer sufficient: we need ways to prove that code is free of bugs. Formal software verification could provide this guarantee, but it has historically required years of expert effort, making it impractical for most real-world projects. In a collaboration with Theorem, however, we show this is no longer the case: LLMs can now produce formal proofs at large scale, enabling new software development workflows that include proven security guarantees. Using Claude, we proved security properties at the assembly code level (RISC-V) in over 100 real-world open-source software libraries. To our knowledge, this represents the first large-scale effort to use AI to apply formal verification to production software at the assembly code level. While writing the proofs, Claude also discovered bugs that had eluded detection for years, despite trillions of test runs. As model capabilities continue to improve, we expect formal verification to become an essential part of secure software development.

#Anthropic#Theorem Labs#Claude#Rocq#RISC-V#OpenSSL#cURL#glibc

Original · 17 min readRead the original
Group chat

No comments yet. Start the conversation.