Real-Time Switched Capacitor Based Power Side-Channel Attack Detection

Side-channel attacks (SCAs) are regarded as significant risks to the hardware implementation of cryptographic systems. Side-channel information, such as timing, power, and electromagnetic radiation, is leaked through the system and can be exploited for secret key extraction. This work proposes a real-time and compatible detection method for power SCAs. The technique utilizes a switched capacitor DC-DC (SC-DCDC) converter in conjunction with a lightweight artificial intelligence engine for power SCA detection. The proposed system, referred to as EoH, possesses the capability to perform dynamic voltage scaling and learn the behaviors of the cryptographic system to identify potential attacks. The switching activities of the SC-DCDC converter can be viewed as measurements of the cryptographic function. Therefore, a recurrent neural network was chosen as it processes time-series data most effectively. The technique is system-specific, meaning that during the enrollment phase, the normal operation of the system is learned. Furthermore, the technique can be expanded to include other types of SCAs and is not limited to power.