Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Computer SecuritySimilar Papers 제목 키워드 기반
Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
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
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
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
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 SelectionAdversarial Feature Selection against Evasion Attacks
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