← Search

Anantha P. Chandrakasan

2 accepted papers

2022

SparseBFA: Attacking Sparse Deep Neural Networks with the Worst-Case Bit Flips on Coordinates

ICASSP 2022accepted

Deep neural networks (DNNs) are shown to be vulnerable to a few carefully chosen bit flips in their parameters, and bit flip attacks (BFAs) exploit such vulnerability to degrade the performance of DNNs. In this work, we show that DNNs with high sparsity that typically result from weight pruning have…

Cited by 0SourceScholar
2018

Energy-Efficient Speaker Identification with Low-Precision Networks

ICASSP 2018accepted

Power-consumption in small devices is dominated by off-chip memory accesses, necessitating small models that can fit in on-chip memory. In the task of text-dependent speaker identification, we demonstrate a 16× byte-size reduction for state-of-art small-footprint LCN/CNN/DNN speaker identification m…

Cited by 0SourceScholar