3 papers
cs.SE2026
UNBIND: UNlearning By INference-time Directional Steering for Code LLMs
Zhengyang Shan, Jiayun Xin, Yanjun Lin +7
Code large language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal. Code unlearning is needed to…
cs.AI2026
OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents
Zhengyang Shan, Xu Qian, Jiayun Xin +3
Large language model agents are becoming operational interfaces to files, memories, registries, and external tools. This deployment shift creates a new skill revocation problem: af…
cs.CR2026
Don't Let the Claw Grip Your Hand: A Security Analysis and Defense Framework for OpenClaw
Zhengyang Shan, Jiayun Xin, Yue Zhang +1
Code agents powered by large language models can execute shell commands on behalf of users, introducing severe security vulnerabilities. This paper presents a two-phase security an…