Book
Open access
Jul 2026
SecMutBench: Evaluating LLM-Generated Security Tests via Mutation-Based Vulnerability Detection
The Security Mutation Score (SMS) is proposed, a metric that classifies mutant kills into semantic, functional, incidental, and crash categories using operator-aware heuristics, distinguishing genuine security awareness from coincidental detection.
Mariam Almutairi, Chang-Tien Lu
· AIware · 0 citations