Game-Theoretic Design of Secure and Resilient Distributed Support Vector Machines with Adversaries
This work addresses security and resilience issues in distributed machine learning systems for networked sensor applications, representing an incremental improvement through the application of game theory to an existing problem.
The paper tackles the vulnerability of distributed support vector machines (DSVMs) to adversarial data manipulation by designing defense strategies using a game-theoretic framework, resulting in algorithms that enhance resilience and show reduced vulnerability with balanced networks and more training samples.
With a large number of sensors and control units in networked systems, distributed support vector machines (DSVMs) play a fundamental role in scalable and efficient multi-sensor classification and prediction tasks. However, DSVMs are vulnerable to adversaries who can modify and generate data to deceive the system to misclassification and misprediction. This work aims to design defense strategies for DSVM learner against a potential adversary. We establish a game-theoretic framework to capture the conflicting interests between the DSVM learner and the attacker. The Nash equilibrium of the game allows predicting the outcome of learning algorithms in adversarial environments, and enhancing the resilience of the machine learning through dynamic distributed learning algorithms. We show that the DSVM learner is less vulnerable when he uses a balanced network with fewer nodes and higher degree. We also show that adding more training samples is an efficient defense strategy against an attacker. We present secure and resilient DSVM algorithms with verification method and rejection method, and show their resiliency against adversary with numerical experiments.