Back to Search
Start Over
Efficient polar coordinates attack with adaptive activation strategy.
- Source :
-
Expert Systems with Applications . Sep2024:Part C, Vol. 249, pN.PAG-N.PAG. 1p. - Publication Year :
- 2024
-
Abstract
- In the realm of decision-based attacks, which aim to mislead target models by manipulating output labels, the advent of the polar coordinates attack has marked a significant evolution. Distinguished by its utilization of sampled affine planes with unique geometrical properties, this method has demonstrated notable enhancements in query efficiency. However, existing implementations of the latest polar coordinates attack encounter two major problems: a contradiction in the update criteria and an overemphasis on allocating query resources to angle binary search. To address these issues, the Efficient Polar Coordinates Attack (EPCA) is introduced, a novel approach that resolves these concerns while significantly augmenting query efficiency. Furthermore, a mechanism termed Adaptive Activation Strategy is proposed to control the deployment of a recently presented plug-and-play module named Frequency Binary Search. The integration of these elements further enables EPCA to effectively circumvent the local optimum. Abundant experiments conducted on the ImageNet dataset demonstrate the exceptional improvements achieved by EPCA, establishing it as a state-of-the-art method in decision-based attacks. The simulation codes of this paper are accessible at https://github.com/RYC-98/EPCA. • Two problems in polar coordinates attacks are revealed. • Efficient Polar Coordinates Attack (EPCA) is used to solve these problems. • An Adaptive Activation Strategy with Frequency Binary Search is proposed. • EPCA attains the SOTA performance. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ARTIFICIAL neural networks
*PROBLEM solving
Subjects
Details
- Language :
- English
- ISSN :
- 09574174
- Volume :
- 249
- Database :
- Academic Search Index
- Journal :
- Expert Systems with Applications
- Publication Type :
- Academic Journal
- Accession number :
- 176785363
- Full Text :
- https://doi.org/10.1016/j.eswa.2024.123850