paper-with-me

홈 › Papers

Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks

2017-04-06 · Yi Han, Benjamin I. P. Rubinstein

Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks---carefully crafted adversarial samples that closely resemble legitimate instances, but cause misclassification. In this paper, we examine the adequacy of the leading approach to generating adversarial samples---the gradient descent approach. In particular (1) we perform extensive experiments on three datasets, MNIST, USPS and Spambase, in order to analyse the effectiveness of the gradient-descent method against non-linear support vector machines, and conclude that carefully reduced kernel smoothness can significantly increase robustness to the attack; (2) we demonstrate that separated inter-class support vectors lead to more secure models, and propose a quantity similar to margin that can efficiently predict potential susceptibility to gradient-descent attacks, before the attack is launched; and (3) we design a new adversarial sample construction algorithm based on optimising the multiplicative ratio of class decision functions.

📄 PDF Abstract BibTeX arXiv:1704.01704

Code (0)

등록된 구현이 없습니다.

Tasks

Computer Security

Similar Papers 제목 키워드 기반

Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks

2020-01-01 · ICML 2020 1 · Sijia Liu, Songtao Lu, Xiangyi Chen, Yao Feng 외

In this paper, we study the problem of constrained min-max optimization in a black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a pri…

When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers

2018-10-31 · Wang Yujia, Miller David J., Kesidis George

This paper addresses detection of a reverse engineering (RE) attack targeting a deep neural network (DNN) image classifier; by querying, RE's aim is to discover the classifier's decision rule. RE can enable test-time eva…

Advanced Evasion Attacks and Mitigations on Practical ML-Based Phishing Website Classifiers

2020-04-15 · Yusi Lei, Sen Chen, Lingling Fan, Fu Song 외

Machine learning (ML) based approaches have been the mainstream solution for anti-phishing detection. When they are deployed on the client-side, ML-based classifiers are vulnerable to evasion attacks. However, such poten…

Evasion Attacks against Machine Learning at Test Time

2017-08-21 · Battista Biggio, Igino Corona, Davide Maiorca, Blaine Nelson 외

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to eva…

BIG-bench Machine LearningMalware DetectionModel Selection

Adversarial Feature Selection against Evasion Attacks

2020-05-25 · Fei Zhang, Patrick P. K. Chan, Battista Biggio, Daniel S. Yeung 외

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion and malware detection, although their security against well-crafted attacks that aim to e…

feature selectionMalware Detection