Evaluation of Four Black-box Adversarial Attacks and Some Query-efficient Improvement Analysis

With the fast development of machine learning technologies, deep learning models have been deployed in almost every aspect of everyday life. However, the privacy and security of these models are threatened by adversarial attacks. Among which black-box attack is closer to reality, where limited knowl...

Full description

Saved in:
Bibliographic Details
Main Author: Wang, Rui
Format: Conference Proceeding
Language:English
Subjects:
black-box adversarial attack
deep learning
query efficiency
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the fast development of machine learning technologies, deep learning models have been deployed in almost every aspect of everyday life. However, the privacy and security of these models are threatened by adversarial attacks. Among which black-box attack is closer to reality, where limited knowledge can be acquired from the model. In this paper, we provided basic background knowledge about adversarial attack and analyzed four black-box attack algorithms: Bandits, NES, Square Attack and ZOsignSGD comprehensively. We also explored the newly proposed Square Attack method with respect to square size, hoping to improve its query efficiency.
ISSN:2166-5656
DOI:10.1109/PHM2022-London52454.2022.00059