Using Bandits for Effective Database Activity Monitoring

Database activity monitoring systems aim to protect organizational data by logging users' activity to Identify and document malicious activity. High-velocity streams and operating costs, restrict these systems to examining only a sample of the activity. Current solutions use manual policies to decide which transactions to monitor. This limits the diversity of the data collected, creating a "filter bubble" over representing specific subsets of the data such as high-risk users and under-representing the rest of the population which may never be sampled. In recommendation systems, Bandit algorithms have recently been used to address this problem. We propose addressing the sampling for database activity monitoring problem as a recommender system. In this work, we redefine the data sampling problem as a special case of the multi-armed bandit problem and present a novel algorithm, C-epsilon-Greedy, which combines expert knowledge with random exploration. We analyze the effect of diversity on coverage and downstream event detection using simulated data. In doing so, we find that adding diversity to the sampling using the bandit-based approach works well for this task, maximizing population coverage without decreasing the quality in terms of issuing alerts about events, and outperforming policies manually crafted by experts and other sampling methods.