CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
Published in , 2026
Authors: Zhen Liang, Jian Zhao, Huilin Zhou, Tianle Zhang, Xuelong Li, Hai Huang
Venue: Status: OpenReview: (profile listing)
First posted: 17 Jan 2026
Last modified: 10 Feb 2026
Recommended citation: Zhen Liang, Jian Zhao, Huilin Zhou, Tianle Zhang, Xuelong Li, Hai Huang. "CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion."
Download Paper