157 citations · 929 across the 89 of their papers we have counts for
7 papers · 1 filter
Performance Comparison of Contemporary DNN Watermarking Techniques
Huili Chen, Bita Darvish Rouhani, Xinwei Fan +2
DNNs shall be considered as the intellectual property (IP) of the model builder due to the impeding cost of designing/training a highly accurate model. Research attempts have been…
Adversarial Reprogramming of Text Classification Neural Networks
Paarth Neekhara, Shehzeen Hussain, Shlomo Dubnov +1
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original net…
RAPIDNN: In-Memory Deep Neural Network Acceleration Framework
Mohsen Imani, Mohammad Samragh, Yeseong Kim +3
Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-the-art D…
DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Models
Bita Darvish Rouhani, Huili Chen, Farinaz Koushanfar
Deep Learning (DL) models have caused a paradigm shift in our ability to comprehend raw data in various important fields, ranging from intelligence warfare and healthcare to autono…
AgileNet: Lightweight Dictionary-based Few-shot Learning
Mohammad Ghasemzadeh, Fang Lin, Bita Darvish Rouhani +2
The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time. With the emergence of intelligent edge applicat…
DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networks
Huili Chen, Bita Darvish Rohani, Farinaz Koushanfar
This paper proposes DeepMarks, a novel end-to-end framework for systematic fingerprinting in the context of Deep Learning (DL). Remarkable progress has been made in the area of dee…
Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications
M. Sadegh Riazi, Christian Weinert, Oleksandr Tkachenko +3
We present Chameleon, a novel hybrid (mixed-protocol) framework for secure function evaluation (SFE) which enables two parties to jointly compute a function without disclosing thei…