Leveraging linear mapping for model-agnostic adversarial defense

Author:

Jamil Huma,Liu Yajing,Blanchard Nathaniel,Kirby Michael,Peterson Chris

Abstract

In the ever-evolving landscape of deep learning, novel designs of neural network architectures have been thought to drive progress by enhancing embedded representations. However, recent findings reveal that the embedded representations of various state-of-the-art models are mappable to one another via a simple linear map, thus challenging the notion that architectural variations are meaningfully distinctive. While these linear maps have been established for traditional non-adversarial datasets, e.g., ImageNet, to our knowledge no work has explored the linear relation between adversarial image representations of these datasets generated by different CNNs. Accurately mapping adversarial images signals the feasibility of generalizing an adversarial defense optimized for a specific network. In this work, we demonstrate the existence of a linear mapping of adversarial inputs between different models that can be exploited to develop such model-agnostic, generalized adversarial defense. We further propose an experimental setup designed to underscore the concept of this model-agnostic defense. We train a linear classifier using both adversarial and non-adversarial embeddings within the defended space. Subsequently, we assess its performance using adversarial embeddings from other models that are mapped to this space. Our approach achieves an AUROC of up to 0.99 for both CIFAR-10 and ImageNet datasets.

Funder

Defense Sciences Office, DARPA

Publisher

Frontiers Media SA

Subject

Computer Science Applications,Computer Vision and Pattern Recognition,Human-Computer Interaction,Computer Science (miscellaneous)

Reference36 articles.

1. “Towards open set deep networks,”;Bendale,2016

2. “A neurobiological evaluation metric for neural network model search,”;Blanchard,2019

3. Threat model-agnostic adversarial defense using diffusion models;Blau;arXiv preprint arXiv:2207.08089,2022

4. On evaluating adversarial robustness;Carlini;arXiv preprint arXiv:1902.06705,2019

5. DAmageNet: a universal adversarial dataset;Chen;arXiv preprint arXiv:1912.07160,2019

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3