paper-with-me

Papers

Evolving Architectures with Gradient Misalignment toward Low Adversarial Transferability

2021-09-13 · Kevin Richard G. Operiano, Wanchalerm Pora, Hitoshi Iba, Hiroshi Kera

Deep neural network image classifiers are known to be susceptible not only to adversarial examples created for them but even those created for others. This phenomenon poses a potential security risk in various black-box systems relying on image classifiers. The reason behind such transferability of adversarial examples is not yet fully understood and many studies have proposed training methods to obtain classifiers with low transferability. In this study, we address this problem from a novel perspective through investigating the contribution of the network architecture to transferability. Specifically, we propose an architecture searching framework that employs neuroevolution to evolve network architectures and the gradient misalignment loss to encourage networks to converge into dissimilar functions after training. Our experiments show that the proposed framework successfully discovers architectures that reduce transferability from four standard networks including ResNet and VGG, while maintaining a good accuracy on unperturbed images. In addition, the evolved networks trained with gradient misalignment exhibit significantly lower transferability compared to standard networks trained with gradient misalignment, which indicates that the network architecture plays an important role in reducing transferability. This study demonstrates that designing or exploring proper network architectures is a promising approach to tackle the transferability issue and train adversarially robust image classifiers.

📄 PDF Abstract BibTeX arXiv:2109.05919

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Residual Connection 설명 없음
Average Pooling 설명 없음
Kaiming Initialization 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Reducing Adversarial Example Transferability Using Gradient Regularization

2019-04-16 · George Adam, Petr Smirnov, Benjamin Haibe-Kains, Anna Goldenberg

Deep learning algorithms have increasingly been shown to lack robustness to simple adversarial examples (AdvX). An equally troubling observation is that these adversarial examples transfer between different architectures…

Common Knowledge Learning for Generating Transferable Adversarial Examples

2023-07-01 · Ruijie Yang, Yuanfang Guo, Junfu Wang, Jiantao Zhou 외

This paper focuses on an important type of black-box attacks, i.e., transfer-based adversarial attacks, where the adversary generates adversarial examples by a substitute (source) model and utilize them to attack an unse…

Improving the Transferability of Adversarial Examples by Inverse Knowledge Distillation

2025-02-24 · Wenyuan Wu, Zheng Liu, Yong Chen, Chao Su 외

In recent years, the rapid development of deep neural networks has brought increased attention to the security and robustness of these models. While existing adversarial attack algorithms have demonstrated success in imp…

Adversarial AttackDiversityKnowledge Distillation

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

2023-07-15 · Yechao Zhang, Shengshan Hu, Leo Yu Zhang, Junyu Shi 외

Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different architectures. Although a bunch of empi…

AttributeData Augmentation

Similarity of Neural Architectures using Adversarial Attack Transferability

2022-10-20 · Jaehui Hwang, Dongyoon Han, Byeongho Heo, Song Park 외

In recent years, many deep neural architectures have been developed for image classification. Whether they are similar or dissimilar and what factors contribute to their (dis)similarities remains curious. To address this…

Adversarial AttackDiversityFeature Importanceimage-classification+2