Aman Mukati

Detecting Adversarial Perturbations in AI-Generated Code: A Three-Tier Detectability Hierarchy

This study investigates adversarial perturbation detection in AI-generated code. We systematically test five perturbation strategies (comment planting, dead code insertion, variable shadowing, import aliasing, boundary inversion) on 550 AI-generated Python samples (100 clean, 450...

Execution-Guided Detection of Semantic Code Perturbations

This paper proposes execution-guided detection: a framework that runs AI-generated code in a sandboxed environment, captures execution traces across diverse test inputs, and classifies code as clean or adversarially perturbed based on behavioral differences. Key findings:- Bounda...

Adversarial Code Review: Can AI Reviewers Be Fooled by Semantic Perturbations?

AI-powered code review tools are increasingly deployed in production environments to automate software quality assurance. However, the security implications of these systems remain underexplored. This paper investigates whether AI code reviewers can be fooled by adversarially per...

Detecting Adversarial Perturbations in AI-Generated Code: A Three-Tier Detectability Hierarchy

This study investigates adversarial perturbation detection in AI-generated code. We systematically test five perturbation strategies (comment planting, dead code insertion, variable shadowing, import aliasing, boundary inversion) on 550 AI-generated Python samples (100 clean, 450...

Execution-Guided Detection of Semantic Code Perturbations

This paper proposes execution-guided detection: a framework that runs AI-generated code in a sandboxed environment, captures execution traces across diverse test inputs, and classifies code as clean or adversarially perturbed based on behavioral differences. Key findings:- Bounda...