Stealthy backdoor attack for code models

• Main Authors: YANG, Zhou, XU, Bowen, ZHANG, Jie M., KANG, Hong Jin, SHI, Jieke, HE, Junda, LO, David
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: Adaptation models; Adversarial Attack; Backdoor Attack; Codes; Data models; Data Poisoning; Grammar; Pre-trained Models of Code; Predictive models; Security; Task analysis; Information Security; Software Engineering
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8699; https://ink.library.smu.edu.sg/context/sis_research/article/9702/viewcontent/StealthyBackdoor_av.pdf
• 機構: Singapore Management University

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to backdoor attacks. A code model that is backdoor-attacked can behav...