Sparsity brings vulnerabilities: Exploring new metrics in backdoor attacks

• Main Authors: TIAN, Jianwen, QIU, Kefan, GAO, Debin, WANG, Zhi, KUANG, Xiaohui, ZHAO, Gang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Backdoors; Boolean features; Candidate selection; Compression strategies; Feature values; Malwares; Model robustness; Numerical features; Problem space; Space constraints; Databases and Information Systems; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/8418; https://ink.library.smu.edu.sg/context/sis_research/article/9421/viewcontent/usenix_23.pdf
• Institution: Singapore Management University

Nowadays, using AI-based detectors to keep pace with the fast iterating of malware has attracted a great attention. However, most AI-based malware detectors use features with vast sparse subspaces to characterize applications, which brings significant vulnerabilities to the model. To exploit this sp...