An LLM-assisted easy-to-trigger poisoning attack on code completion models: Injecting disguised vulnerabilities against strong detection

• Main Authors: YAN, Shenao, WANG, Shen, DUAN, Yue, HONG, Hanbin, LEE, Kiho, KIM, Doowon, HONG, Yuan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/8962; https://ink.library.smu.edu.sg/context/sis_research/article/9965/viewcontent/2406.06822v1.pdf
• Institution: Singapore Management University

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and backdoor attacks can covertly alter the model outputs. To a...