Application Inference using Machine Learning based Side Channel Analysis

Abstract

The proliferation of ubiquitous computing requires energy-efficient as well as secure operation of modern processors. Side channel attacks are becoming a critical threat to security and privacy of devices embedded in modern computing infrastructures. Unintended information leakage via physical signatures such as power consumption, electromagnetic emission (EM) and execution time have emerged as a key security consideration for SoCs. Also, information published on purpose at user privilege level accessible through software interfaces results in softwareonly attacks. In this paper, we used a supervised learning based approach for inferring applications executing on android platform based on features extracted from EM side-channel emissions and software exposed dynamic voltage frequency scaling (DVFS) states. We highlight the importance of machine learning based approach in utilizing these multi-dimensional features on a complex SoC, against profiling-based approaches. We also show that learning the instantaneous frequency states polled from onboard frequency driver (cpufreq) is adequate to identify a known application and flag potentially malicious unknown application. The experimental results on benchmarking applications running on ARMv8 processor in Snapdragon 820 board demonstrates early detection of these apps, and atleast 85% accuracy in detecting unknown applications. Overall, the highlight is to utilize a low-complexity path to application inference attacks through learning instantaneous frequency states pattern of CPU core.

Optimizing Power Management in IoT Devices Using Machine Learning Techniques

“…An agent learns to make decisions by interacting with its environment in order to maximize cumulative rewards in reinforcement learning, a subfield of machine learning. RL is a promising strategy for adaptive power optimization in IoT devices because it is well-suited for dynamic and uncertain environments [9].…”

Forensic Insights From Smartphones Through Electromagnetic Side-Channel Analysis

“…For example, it is possible to identify cryptographic operations [8], sorting algorithms [12], and specific known software behaviours [13] on embedded systems such as Arduino and Raspberry Pi devices. Chawla et al performed application inference on a SoC processor running Android operating system by utilising a combination of EM radiation and dynamic voltage frequency scaling (DVFS) information from the CPU driver [14]. In order to acquire forensic insights from smartphones in digital forensic scenarios, it is important to explore the potential of using such methods under realistic scenarios on actual smartphones.…”

“…Similarly, another potential problem that adds up to this situation is the use of dynamic voltage frequency scaling (DVFS) techniques in modern processors [14]. It allows a SoC processor to dynamically adjust its clock frequencies according to workload.…”

Electromagnetic Side-Channel Analysis for IoT Forensics: Challenges, Framework, and Datasets

“…Therefore, modern SoC processors that are included in smartphones and IoT devices tend to use various techniques for performance improvement while being efficient at energy consumption. One such common technique is the dynamic voltage-frequency scaling (DVFS) [34] where the CPU cores of a processor dynamically adjusts its clock frequency according to the workload; the higher the workload, the faster the CPU cores are running. Another techniques is the use of multiple CPU core clusters that are fixed to run at different clock frequencies, e.g., ARM's big.LITTLE technology [35].…”