IoT Checker Using Timing Side-Channel and Machine Learning
Communications in Computer and Information Science
In the recent era, the adoption of IoT technology can be seen in nearly every other field. However, with its fast growth rate, the IoT brings several advanced security challenges. To alleviate these problems, we propose an inventive framework introduced into the IoT package to gather side-channel information (execution timing) for inconsistency and attack location. We observed that the applications running on the gadget would need more time to execute during the attack as the resources such as memory, I/O, CPU will get drained. This timing information under normal and attack mode will be extracted, processed, and utilized to construct a fingerprint. The support vector machine method will then be used to identify if the device is under attack utilizing the fingerprint.
IoT security, Machine learning, Side-channel-attack
Kratika Sahu, Rasika Kshirsagar, Surbhi Vasudeva, Taghreed Alzahrani, and Nima Karimian. "IoT Checker Using Timing Side-Channel and Machine Learning" Communications in Computer and Information Science (2021): 220-226. https://doi.org/10.1007/978-3-030-72725-3_16