phenomenon · first seen 4 Oct 2026
adversarial attacks on LLM code review
Also: prompt injection on AI code reviewers
Manipulating AI reviewers of pull requests to approve vulnerable code through crafted changes or feedback.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Adaptive Code Revision Attacks on AI Pull Request ReviewersPapers · 4 Oct 2026 · Jingzhi Gong, Jie M. Zhang, Gunel Jahangirova, Meng Wang
Latest sources
- Adaptive Code Revision Attacks on AI Pull Request ReviewersPapers · 4 Oct 2026 · Jingzhi Gong, Jie M. Zhang, Gunel Jahangirova, Meng Wang