Evasion Attack of Multi-class Linear Classifiers
نویسندگان
چکیده
Machine learning has yield significant advances in decision-making for complex systems, but are they robust against adversarial attacks? We generalize the evasion attack problem to the multi-class linear classifiers, and present an efficient algorithm for approximating the optimal disguised instance. Experiments on real-world data demonstrate the effectiveness of our method.
منابع مشابه
Feature-based Malicious URL and Attack Type Detection Using Multi-class Classification
Nowadays, malicious URLs are the common threat to the businesses, social networks, net-banking etc. Existing approaches have focused on binary detection i.e. either the URL is malicious or benign. Very few literature is found which focused on the detection of malicious URLs and their attack types. Hence, it becomes necessary to know the attack type and adopt an effective countermeasure. This pa...
متن کاملThe Comparison of Multi-variable Linear Regression and Artificial Neutral Networks in Tax Evasion of Legal Persons in Iranian Tax System
Tax evasion is one of the most important problems of tax system in the most countries around the world. It covers any unlawful attempt to avoid paying taxes. In present study, the affective factors on tax evasion based on experts’ views were extracted by using Delphi method, so we identified 29 factors and finally 16 factors were extracted based on measurement ability among them. The statistica...
متن کاملHardening Classifiers against Evasion: the Good, the Bad, and the Ugly
Machine learning is widely used in security applications, particularly in the form of statistical classification aimed at distinguishing benign from malicious entities. Recent research has shown that such classifiers are often vulnerable to evasion attacks, whereby adversaries change behavior to be categorized as benign while preserving malicious functionality. Research into evasion attacks has...
متن کاملOn Security and Sparsity of Linear Classifiers for Adversarial Settings
Machine-learning techniques are widely used in security-related applications, like spam and malware detection. However, in such settings, they have been shown to be vulnerable to adversarial attacks, including the deliberate manipulation of data at test time to evade detection. In this work, we focus on the vulnerability of linear classifiers to evasion attacks. This can be considered a relevan...
متن کاملOne-and-a-Half-Class Multiple Classifier Systems for Secure Learning Against Evasion Attacks at Test Time
Pattern classifiers have been widely used in adversarial settings like spam and malware detection, although they have not been originally designed to cope with intelligent attackers that manipulate data at test time to evade detection. While a number of adversary-aware learning algorithms have been proposed, they are computationally demanding and aim to counter specific kinds of adversarial dat...
متن کامل