Randomized Prediction Games for Adversarial Machine Learning

Abstract

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 hide known exploits. Interestingly, randomization has also been proposed to improve security of learning algorithms against evasion attacks, as it results in hiding information about the classifier to the attacker. Recent work has proposed game-theoretical formulations to learn secure classifiers, by simulating different evasion attacks and modifying the classification function accordingly. However, both the classification function and the simulated data manipulations have been modeled in a deterministic manner, without accounting for any form of randomization. In this work, we overcome this limitation by proposing a randomized prediction game, namely, a non-cooperative game-theoretic formulation in which the classifier and the attacker make randomized strategy selections according to some probability distribution defined over the respective strategy set. We show that our approach allows one to improve the trade-off between attack detection and false alarms with respect to state-of-the-art secure classifiers, even against attacks that are different from those hypothesized during design, on application examples including handwritten digit recognition, spam and malware detection.

References in corpus (5)

• Evasion Attacks against Machine Learning at Test Time
• Poisoning Attacks against Support Vector Machines
• Security Evaluation of Pattern Classifiers under Attack
• Is feature selection secure against training data poisoning?
• Stackelberg vs. Nash in Security Games: An Extended Investigation of Interchangeability, Equivalence, and Uniqueness

Cited by in corpus (16)

• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Adversarial Examples: Opportunities and Challenges
• Towards Adversarial Malware Detection: Lessons Learned from PDF-based Attacks
• A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Tasks
• Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks
• A Game-Theoretic Approach to Design Secure and Resilient Distributed Support Vector Machines
• Randomization matters. How to defend against strong adversarial attacks
• Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
• ROBY: Evaluating the Robustness of a Deep Model by its Decision Boundaries
• Mixed Nash Equilibria in the Adversarial Examples Game
• Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent
• Securing Behavior-based Opinion Spam Detection
• Training Set Camouflage
• Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challenges
• Towards Optimal Randomized Strategies in Adversarial Example Game
• Scalable Optimal Classifiers for Adversarial Settings under Uncertainty