Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Adnan Siraj Rakin"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:7928-7939
Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack.Recently, another dimension of adversarial attack, namely, attack on DNN weight parameters, has been shown to be very powerful. Asa re
Autor:
Sai Kiran Cherupally, Jian Meng, Adnan Siraj Rakin, Shihui Yin, Mingoo Seok, Deliang Fan, Jae-Sun Seo
Publikováno v:
IEEE Design & Test. 39:71-80
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
This work aims to tackle Model Inversion (MI) attack on Split Federated Learning (SFL). SFL is a recent distributed training scheme where multiple clients send intermediate activations (i.e., feature map), instead of raw data, to a central server. Wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::56ca8e0a1392eb26608207abb0ba9e66
http://arxiv.org/abs/2205.04007
http://arxiv.org/abs/2205.04007
Publikováno v:
ACM Journal on Emerging Technologies in Computing Systems. 16:1-24
In this work, we propose a multiplication-less binarized depthwise-separable convolution neural network, called BD-Net. BD-Net is designed to use binarized depthwise separable convolution block as the drop-in replacement of conventional spatial-convo
Publikováno v:
2021 IEEE International Symposium on Hardware Oriented Security and Trust (HOST).
Neural network stealing attacks have posed grave threats to neural network model deployment. Such attacks can be launched by extracting neural architecture information, such as layer sequence and dimension parameters, through leaky side-channels. To
Publikováno v:
DAC
In-memory computing (IMC) substantially improves the energy efficiency of deep neural network (DNNs) hardware by activating many rows together and performing analog computing. The noisy analog IMC induces some amount of accuracy drop in hardware acce
Publikováno v:
ISIT
Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples. Our work draws the connection between optimal robust learning and the privacy-utility tradeoff problem, which is