ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

TL;DR

ASTRA is an automated system that systematically uncovers safety flaws in AI code assistants by exploring complex software tasks and generating realistic vulnerability cases, improving safety testing effectiveness.

Contribution

ASTRA introduces a novel three-stage approach combining knowledge graphs and adaptive probing to identify vulnerabilities in AI code assistants more effectively than prior methods.

Findings

Finds 11-66% more issues than existing techniques.

Generates test cases that improve model alignment by 17%.

Demonstrates practical value for safer AI systems.

Abstract

AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecurity. Current red-teaming tools often rely on fixed benchmarks or unrealistic prompts, missing many real-world vulnerabilities. We present ASTRA, an automated agent system designed to systematically uncover safety flaws in AI-driven code generation and security guidance systems. ASTRA works in three stages: (1) it builds structured domain-specific knowledge graphs that model complex software tasks and known weaknesses; (2) it performs online vulnerability exploration of each target model by adaptively probing both its input space, i.e., the spatial exploration, and its reasoning processes, i.e., the temporal exploration, guided by the knowledge graphs; and (3) it generates high-quality violation-inducing cases to improve model alignment. Unlike prior methods, ASTRA focuses on realistic inputs-requests that developers might actually ask-and uses both offline abstraction guided domain modeling and online domain knowledge graph adaptation to surface corner-case vulnerabilities. Across two major evaluation domains, ASTRA finds 11-66% more issues than existing techniques and produces test cases that lead to 17% more effective alignment training, showing its practical value for building safer AI systems.