Security of Deep Learning Methodologies: Challenges and Opportunities

12/08/2019
by   Shahbaz Rezaei, et al.
32

Despite the plethora of studies about security vulnerabilities and defenses of deep learning models, security aspects of deep learning methodologies, such as transfer learning, have been rarely studied. In this article, we highlight the security challenges and research opportunities of these methodologies, focusing on vulnerabilities and attacks unique to them.

READ FULL TEXT

page 1

page 3

page 6

research
04/07/2022

Security Aspects of Quantum Machine Learning: Opportunities, Threats and Defenses

In the last few years, quantum computing has experienced a growth spurt....
research
06/16/2021

Side-Channel Attacks on RISC-V Processors: Current Progress, Challenges, and Opportunities

Side-channel attacks on microprocessors, like the RISC-V, exhibit securi...
research
11/29/2017

Security Risks in Deep Learning Implementations

Advance in deep learning algorithms overshadows their security risk in s...
research
07/12/2018

When deep learning meets security

Deep learning is an emerging research field that has proven its effectiv...
research
09/07/2023

A New Model for Testing IPv6 Fragment Handling

Since the origins of the Internet, various vulnerabilities exploiting th...
research
11/29/2022

Backdoor Vulnerabilities in Normally Trained Deep Learning Models

We conduct a systematic study of backdoor vulnerabilities in normally tr...
research
03/31/2018

A Survey of Techniques for Improving Security of GPUs

Graphics processing unit (GPU), although a powerful performance-booster,...

Please sign up or login with your details

Forgot password? Click here to reset