all InfoSec news
PowerGAN: A Machine Learning Approach for Power Side-Channel Attack on Compute-in-Memory Accelerators. (arXiv:2304.11056v1 [cs.CR])
cs.CR updates on arXiv.org arxiv.org
Analog compute-in-memory (CIM) accelerators are becoming increasingly popular
for deep neural network (DNN) inference due to their energy efficiency and
in-situ vector-matrix multiplication (VMM) capabilities. However, as the use of
DNNs expands, protecting user input privacy has become increasingly important.
In this paper, we identify a security vulnerability wherein an adversary can
reconstruct the user's private input data from a power side-channel attack,
under proper data acquisition and pre-processing, even without knowledge of the
DNN model. We further demonstrate a …
acquisition adversary attack capabilities channel compute data efficiency energy identify important input knowledge machine machine learning matrix memory network neural network popular power privacy protecting security security vulnerability side-channel side-channel attack under vulnerability