Multitask adversarial attack with dispersion amplification

Multitask adversarial attack with dispersion amplification

Abstract Recently, adversarial attacks have drawn the community’s attention as an effective tool to degrade the accuracy of neural networks. However, their actual usage in the world is limited. The main reason is that real-world machine learning systems, such as content filters or face detectors, of...

Full description

Bibliographic Details
Main Authors: Pavlo Haleta, Dmytro Likhomanov, Oleksandra Sokol
Format: Article
Language:English
Published: SpringerOpen 2021-09-01
Series:EURASIP Journal on Information Security
Subjects:
Adversarial attack
Neural network
Multitask adversarial attack
Attack transferability
Online Access:https://doi.org/10.1186/s13635-021-00124-3

Internet

https://doi.org/10.1186/s13635-021-00124-3

Similar Items