FDI : Attack neural code generation systems through user feedback channel

• Main Authors: SUN, Zhensu, DU, Xiaoning, LUO, Xiapu, SONG, Fu, LO, David, LI, Li
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Code generation; Data poisoning; User feedback; Security and privacy; Feedback data injection; Artificial Intelligence and Robotics; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/9885; https://ink.library.smu.edu.sg/context/sis_research/article/10885/viewcontent/2408.04194v1.pdf
• Institution: Singapore Management University

Neural code generation systems have recently attracted increasing attention to improve developer productivity and speed up software development. Typically, these systems maintain a pre-trained neural model and make it available to general users as a service (e.g., through remote APIs) and incorporat...