Power-aware anomaly detection in smartphones: An analysis of on-platform versus externalized operation

• We assess the power-consumption trade-offs among different strategies for off-loading, or not, certain security tasks to the cloud.
• We evaluate different functional tasks in machine learning based detection systems.
• We provide consumption models for such tasks that can be used to obtain power consumption estimates and compare detectors.
• Experiments show that outsourced computation is significantly the best option in terms of power consumption.
• Our findings also point out noticeable differences among different machine learning algorithms.

Many security problems in smartphones and other smart devices are approached from an anomaly detection perspective in which the main goal reduces to identifying anomalous activity patterns. Since machine learning algorithms are generally used to build such detectors, one major challenge is adapting these techniques to battery-powered devices. Many recent works simply assume that on-platform detection is prohibitive and suggest using offloaded (i.e., cloud-based) engines. Such a strategy seeks to save battery life by exchanging computation and communication costs, but it still remains unclear whether this is optimal or not in all circumstances. In this paper, we evaluate different strategies for offloading certain functional tasks in machine learning based detection systems. Our experimental results confirm the intuition that outsourced computation is clearly the best option in terms of power consumption, outweighing on-platform strategies in, essentially, all practical scenarios. Our findings also point out noticeable differences among different machine learning algorithms, and we provide separate consumption models for functional blocks (data preprocessing, training, test, and communications) that can be used to obtain power consumption estimates and compare detectors.