UAP4MA: Leveraging Multi-Agent Bandits to Generate Universal Adversarial Perturbations for Malware Attribution

This research presents UAP4MA, a method for generating universal adversarial perturbations (UAPs, which are small modifications that can fool AI models across many different inputs) that can deceive malware attribution models used to identify which criminal group created specific malware. The method uses a multi-agent Multi-Armed Bandit framework (a system where multiple decision-making agents work together to explore different options and find the best ones) to create these perturbations more effectively and efficiently than previous approaches.