Home
Resource
CAG: a real-time low-cost enhanced-robustness high-transferability content-aware adversarial attack generator
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(818.40 kb)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Phan, Van Nhat Huy. CAG: a real-time low-cost enhanced-robustness high-transferability content-aware adversarial attack generator. Retrieved from https://doi.org/doi:10.7282/t3-2qty-qp77

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleCAG: a real-time low-cost enhanced-robustness high-transferability content-aware adversarial attack generator
NamePhan, Van Nhat Huy (author); Yuan, Bo (chair); Soljanin, Emina (internal member); Wei, Sheng (internal member); Sarwarte, Anand (internal member); Rutgers University; School of Graduate Studies
Date Created2020
Other Date2020-05 (degree)
SubjectArtificial intelligence, Electrical and Computer Engineering
Extent1 online resource (viii, 24 pages) : illustrations
DescriptionDeep neural networks (DNNs) are vulnerable to adversarial attack despite their tremendous success in many artificial intelligence fields. Adversarial attack is a method that causes the intended misclassfication by adding imperceptible perturbations to legitimate inputs. To date, researchers have developed numerous types of adversarial attack methods. However, from the perspective of practical deployment, these methods suffer from several drawbacks such as long attack generating time, high memory cost, insufficient robustness and low transferability. To address the drawbacks, we propose a Content-aware Adversarial Attack Generator (CAG) to achieve real-time, low-cost, enhanced-robustness and high-transferability adversarial attack. First, as a type of generative model-based attack, CAG shows significant speedup (at least 500 times) in generating adversarial examples compared to the state-of-the-art attacks such as PGD and C&W. Furthermore, CAG only needs a single generative model to perform targeted attack to any targeted class. Because CAG encodes the label information into a trainable embedding layer, it differs from prior generative model-based adversarial attacks that use $n$ different copies of generative models for $n$ different targeted classes. As a result, CAG significantly reduces the required memory cost for generating adversarial examples. Moreover, CAG can generate adversarial perturbations that focus on the critical areas of input by integrating the class activation maps information in the training process, and hence improve the robustness of CAG attack against the state-of-art adversarial defenses. In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations. Extensive experiments on different datasets and DNN models have verified the real-time, low-cost, enhanced-robustness, and high-transferability benefits of CAG.
NoteM.S.
NoteIncludes bibliographical references
Genretheses, ETD graduate
Persistent URLhttps://doi.org/doi:10.7282/t3-2qty-qp77
LanguageEnglish
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024