Investigation of Transfer Learning Efficiency in Adversarial Attacks

Investigation of Transfer Learning Efficiency in Adversarial Attacks

Deep neural networks are becoming an increasingly effective tool for solving a wide range of complex applied tasks, because they are able to establish patterns in unstructured data, such as images, video and audio information. Despite the fact that the probability of error of modern neural network m...

Full description

Bibliographic Details
Main Authors: Denis I. Parfenov, Irina P. Bolodurina, Lyubov S. Grishina, Artur Yu. Zhigalov, Sergey V. Tolmachev
Format: Article
Language:Russian
Published: The Fund for Promotion of Internet media, IT education, human development «League Internet Media» 2022-12-01
Series:Современные информационные технологии и IT-образование
Subjects:
convolutional neural network
adversarial attacks
transfer learning
image recognition
automotive unmanned transport networks
Online Access:http://sitito.cs.msu.ru/index.php/SITITO/article/view/925

Internet

http://sitito.cs.msu.ru/index.php/SITITO/article/view/925

Similar Items