38 citations · 45 across the 5 of their papers we have counts for
3 papers · 1 filter
Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs
Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar +3
Existing deep neural networks (DNNs) that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on either activation or weight condition…
Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference
Souvik Kundu, Shunlin Lu, Yuke Zhang +2
The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce…
BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch
Souvik Kundu, Shikai Wang, Qirui Sun +2
Large DNNs with mixed-precision quantization can achieve ultra-high compression while retaining high classification performance. However, because of the challenges in finding an ac…