Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities

2026-06-25

AI Summary

Existing AI-based approaches struggle to effectively detect cryptographic misuse vulnerabilities due to the absence of clear signals analogous to those in memory safety. This work proposes a novel paradigm that leverages AI-driven differential testing to identify genuine vulnerabilities by analyzing natural behavioral discrepancies across cryptographic libraries. By integrating dependency graphs, the approach propagates findings downstream, enabling a shift from auditing multiple defects within a single library to cataloging library-level flaws and disseminating them across projects. The method substantially enhances both the efficiency and precision of vulnerability discovery, having already uncovered over one hundred vulnerabilities—including a critical flaw in an SSL library affecting billions of devices, as well as key issues in mainstream web browsers and Linux distributions.

Abstract

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.

Problem

• cryptographic misuse
• vulnerability discovery
• AI-assisted security
• differential testing
• security validation

Innovation

• cryptographic misuse
• AI-assisted vulnerability discovery
• differential testing
• dependency graph propagation
• security validation