Related papers: Classification under strategic adversary manipulat…
We consider pessimistic bilevel stochastic programs in which the follower maximizes over a fixed compact convex set a strictly convex quadratic function, whose Hessian depends on the leader's decision. The resulting random variable is…
Adversarial learning has been attracting more and more attention thanks to the fast development of machine learning and artificial intelligence. However, due to the complicated structure of most machine learning models, the mechanism of…
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…
Machine learning (ML) models are often sensitive to carefully crafted yet seemingly unnoticeable perturbations. Such adversarial examples are considered to be a property of ML models, often associated with their black-box operation and…
Decentralized machine learning often relies on outsourcing computations, such as gradient evaluations, to untrusted worker nodes. Existing robust aggregation methods can mitigate malicious behavior under honest-majority assumptions, but may…
The rise of computer vision applications in the real world puts the security of the deep neural networks at risk. Recent works demonstrate that convolutional neural networks are susceptible to adversarial examples - where the input images…
Adversarial examples are inputs to a machine learning system that result in an incorrect output from that system. Attacks launched through this type of input can cause severe consequences: for example, in the field of image recognition, a…
It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…
Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…
In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e.g., malware code is typically obfuscated using random strings or byte sequences to…
Machine learning algorithms are used to construct a mathematical model for a system based on training data. Such a model is capable of making highly accurate predictions without being explicitly programmed to do so. These techniques have a…
Machine learning based solutions have been very helpful in solving problems that deal with immense amounts of data, such as malware detection and classification. However, deep neural networks have been found to be vulnerable to adversarial…
Model extraction attacks have become serious issues for service providers using machine learning. We consider an adversarial setting to prevent model extraction under the assumption that attackers will make their best guess on the service…
As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…
State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to defend against such examples. It is formulated as a min-max…
We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the…
Classification problems in security settings are usually contemplated as confrontations in which one or more adversaries try to fool a classifier to obtain a benefit. Most approaches to such adversarial classification problems have focused…
In this work, we propose different formulations and gradient-based algorithms for deterministic and stochastic bilevel problems with conflicting objectives in the lower level. Such problems have received little attention in the…
Machine learning techniques are currently used extensively for automating various cybersecurity tasks. Most of these techniques utilize supervised learning algorithms that rely on training the algorithm to classify incoming data into…
Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…