Massively Parallel Evasion Attacks and the Pitfalls of Adversarial Retraining

Author:

Meyers Charles,Löfstedt Tommy,Elmroth Erik

Abstract

Even with widespread adoption of automated anomaly detection in safety-critical areas, both classical and advanced machine learning models are susceptible to first-order evasion attacks that fool models at run-time (e.g. an automated firewall or an anti-virus application). Kernelized support vector machines (KSVMs) are an especially useful model because they combine a complex geometry with low run-time requirements (e.g. when compared to neural networks), acting as a run-time lower bound when compared to contemporary models (e.g. deep neural networks), to provide a cost-efficient way to measure model and attack run-time costs. To properly measure and combat adversaries, we propose a massively parallel projected gradient descent (PGD) evasion attack framework. Through theoretical examinations and experiments carried out using linearly-separable Gaussian normal data, we present (i) a massively parallel naive attack, we show that adversarial retraining is unlikely to be an effective means to combat an attacker even on linearly separable datasets, (ii) a cost effective way of evaluating models defences and attacks, and an extensible code base for doing so, (iii) an inverse relationship between adversarial robustness and benign accuracy, (iv) the lack of a general relationship between attack time and efficacy, and (v) that adversarial retraining increases compute time exponentially while failing to reliably prevent highly-confident false classifications.

Publisher

European Alliance for Innovation n.o.

Reference57 articles.

1. Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I. and Fergus, R. (2013) Intriguing properties of neural networks. International Conference on Learning Representations.

2. Madry, A., Makelov, A., Schmidt, L., Tsipras, D. and Vladu, A. (2017) Towards deep learning models resistant to adversarial attacks. International Conference on Machine Learning.

3. Croce, F. and Hein, M. (2020) Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks. International Conference on Machine Learning.

4. Deka, P.K., Bhuyan, M.H., Kadobayashi, Y. and Elmroth, E. (2019) Adversarial impact on anomaly detection in cloud datacenters. In 2019 IEEE 24th Pacific Rim International Symposium on Dependable Computing (PRDC) (IEEE): 188–18809.

5. Kim, D.S. and Park, J.S. (2003) Network-based intrusion detection with support vector machines. In International Conference on Information Networking (Springer): 747–756.

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