Oct 25, 2026
CyberDual evaluates AI attackers planting memory-safety defects against AI code reviewers on real maintenance contexts
Yang and colleagues present CyberDual, testing AI-planted memory-safety defects in real C/C++ maintenance contexts against agentic review and repair. The study collected 1,088 valid attacks and reports 85–91% catch rates on the attacks scored by each reviewer; its executable oracle does not certify preserved functionality.