Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities
For developers and security researchers, Chai addresses the lack of instrumentation for cryptographic misuse vulnerabilities, enabling automated discovery of real-world security flaws in widely-used libraries.
Chai introduces an AI-driven system that discovers and validates cryptographic misuse vulnerabilities by rethinking differential testing, leveraging AI to improve precision and propagate library-level flaws across dependency graphs. It uncovered over 100 vulnerabilities, including a critical bug in an SSL library used by billions of devices.
AI-assisted vulnerability discovery has proven effective for bug classes like memory safety, where instrumentation confirms memory violations and efficiently filters false positives. Many dangerous vulnerability classes, such as cryptographic misuse, however, lack any comparable instrumentation. In this work, we present Chai, an AI-based system that discovers and validates cryptographic misuse vulnerabilities through naturally occurring signals. To achieve this, Chai rethinks the classical technique of differential testing by leveraging AI to 1) improve precision for detecting real security issues in libraries, and 2) repurpose commonly overlooked discrepancies as leads for tangible vulnerabilities in downstream applications. In doing so, Chai inverts the prevailing paradigm of AI vulnerability discovery: instead of auditing one codebase for many flaws, it catalogs flaws at the library level and propagates them across a cryptographic dependency graph, delivering compounding efficiency gains. We evaluate Chai across X.509, JWT, and SAML libraries. Chai discovered a previously unknown critical vulnerability in an SSL library that powers billions of devices, along with security bugs in one library behind a major web browser and another in major Linux distributions. In total, these techniques surfaced over 100 vulnerabilities.