LeakSEAL: Power Side-Channel Leakage Analysis and Mitigation for Secure Edge AI Learning

On-chip learning enables machine learning models to be trained or updated directly on specialized hardware rather than on external CPUs or GPUs, offering lower latency, improved energy-efficiency, enhanced privacy, and real-time adaptability for edge devices. In Spiking Neural Networks (SNNs), this capability relies on dynamic synaptic weight adaptation, but such adaptability also introduces significant security risks. In this work, we demonstrate a power side-channel attack on a quantized SNN implemented on a CW305 FPGA platform using ChipWhisperer. Our analysis identifies consistent power leakage patterns associated with neuron update operations, allowing an attacker to infer internal model attributes without direct access to the model's weights or inputs. We further perform Correlation Power Analysis (CPA) with a Hamming Weight leakage model to recover secret synaptic weights with high confidence using as few as 1,500 power traces. These results expose critical vulnerabilities in on-chip learning systems and SNN architectures, highlight realistic threats to IoT and edge applications, and motivate mitigation strategies at the software-hardware boundary, including secure design practices, cryptographic protections, and access control mechanisms, without significantly degrading performance.