Machine learning through cryptographic glasses: combating adversarial attacks by key-based diversified aggregation

Machine learning through cryptographic glasses: combating adversarial attacks by key-based diversified aggregation

Abstract In recent years, classification techniques based on deep neural networks (DNN) were widely used in many fields such as computer vision, natural language processing, and self-driving cars. However, the vulnerability of the DNN-based classification systems to adversarial attacks questions the...

Full description

Bibliographic Details
Main Authors: Olga Taran, Shideh Rezaeifar, Taras Holotyak, Slava Voloshynovskiy
Format: Article
Language:English
Published: SpringerOpen 2020-06-01
Series:EURASIP Journal on Information Security
Subjects:
Adversarial examples
Defense
Randomization
Diversified aggregation
Black-box attacks
Non-gradient/gradient-based attacks
Online Access:http://link.springer.com/article/10.1186/s13635-020-00106-x

Internet

http://link.springer.com/article/10.1186/s13635-020-00106-x

Similar Items