]> 2026-04-04T18:09:22+02:00 Profiling ML Side-Channel on CiM for Input Reconstruction 0 en Master investigate whether supervised models (e.g., U-Net/pix2pix) can reconstruct pri- vate inputs from CiM-generated “power-feature matrices” and how noise/sampling constrain feasibility. Wang, Ziyu, et al. "PowerGAN: a machine learning approach for power side‐channel attack on compute‐in‐memory accelerators." Advanced Intelligent Systems 5.12 (2023): 2300313. Open Spring 2026 (Jan–Jun) Profiling ML Side-Channel on CiM for Input Reconstruction 2025-10-21T14:52:46Z 2460970.1199769 Profiling ML Side-Channel on CiM for Input Reconstruction