Anthropic Releases Open Source Library for Large-Scale Formal Verification of Claude

Artificial intelligence company Anthropic's Frontier Red Team released a study on October 22, stating that large language models can now automatically write formal proofs on a larger scale. The team collaborated with Theorem to use Claude to prove safety properties for over 100 real open-source libraries at the RISC-V assembly level, marking the first time AI has been used for large-scale formal verification of production software at the assembly level. During the proof-writing process, previously undiscovered vulnerabilities were found. The experiment converted existing compilable fuzz tests from Google OSS-Fuzz into specifications, under assumptions of single-threaded static binaries, fixed memory budgets, RISC-V CPUs, and Linux, ensuring that for any input less than 64 MB, the program should exit normally without triggering memory safety errors or assertion failures. After addressing the issues, Claude proved the aforementioned properties for 239 entry points across 123 OSS-Fuzz libraries, demonstrating that approximately 180 million lines of Rocq were verified against compiled RISC-V instructions, checked by the Rocq kernel. The page notes that this does not mean these libraries are free of vulnerabilities, as remaining issues may lie within trusted components or outside the scope of the proofs. The team also had Claude formalize RFC 1950 and proved that the zlib implementation in the Linux kernel conforms to this specification at the x86 binary level; an interpreter written in Rust covering a large subset of Python achieved a 99.95% consistency with CPython behavior across over 1.7 million randomly generated programs. In 36 small verification tasks, Opus 5.5 proved that it required about 40% fewer tokens than Opus 5 for half of them.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.