An Effective Adversarial Defense Framework: From Robust Feature Perspective
Deep neural networks are known to be vulnerable to adversarial attacks. Unfortunately, the underlying mechanisms remain insufficiently understood, leading to empirical defenses that often fail against new attacks. In this pap... | Find, read and cite all the research you need on Tech Science Press
Authors
- Xinlei Liu (ORCID: https://orcid.org/0009-0000-0139-349X)
- Peng Yi (ORCID: https://orcid.org/0000-0001-9366-951X)
- Baolin Li (ORCID: https://orcid.org/0000-0002-2743-2570)
- Tao Hu (ORCID: https://orcid.org/0000-0002-7712-5851)
- Jichao Xie (ORCID: https://orcid.org/0000-0002-3075-188X)
Publication Details
- Journal
- Computers, materials & continua/Computers, materials & continua (Print)
- Published
- 2025-01-01
- DOI
- https://doi.org/10.32604/cmc.2025.066370
- Citations
- 1
- Primary Topic
- Anomaly Detection Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- National Natural Science Foundation of China
- Ministry of Education of the People's Republic of China