Sparsity brings vulnerabilities: Exploring new metrics in backdoor attacks
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...
Saved in:
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: | |
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 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
INDUSTRIAL SPACE USER REQUIREMENTS
by: LYE FOONG YEE
Published: (2020) -
Recognizing manufacturing features from a design-by-feature model
by: Li, W.D., et al.
Published: (2014) -
Analysis and detection of human emotion and stress from speech signals
by: TIN LAY NWE
Published: (2010) -
SampDetox : Black-box backdoor defense via perturbation-based sample detoxification
by: YANG, Yanxin, et al.
Published: (2024) -
Automatic recognition of design and machining features from prismatic parts
by: Senthil Kumar, A., et al.
Published: (2014)