Not All Adversarial Comments Are Equal: A Ranked Empirical Study of Twelve Comment Injection Attacks Against LLM-Based Code Vulnerability Detection
Sunny Chokshi. 2nd IEEE International Conference on Cyber-AI (Cyber-AI 2026), Bucharest, Romania, September 2026. To appear in IEEE Xplore.
Download the PDF (accepted author version)
© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.