no code implementations • 31 Oct 2019 • Vasisht Duddu, D. Vijay Rao
While the attacks proposed in literature are empirical, there is a need for a theoretical framework to measure the information leaked under such extraction attacks.
no code implementations • 30 Oct 2019 • Vasisht Duddu, N. Rajesh Pillai, D. Vijay Rao, Valentina E. Balas
Specifically, this work studies the impact of the fault tolerance of the Neural Network on training the model by adding noise to the input (Adversarial Robustness) and noise to the gradients (Differential Privacy).
1 code implementation • 6 Jul 2019 • Vasisht Duddu, D. Vijay Rao, Valentina E. Balas
In the view of difference in functionality, a Neural Network is modelled as two separate networks, i. e, the Feature Extractor with unsupervised learning objective and the Classifier with a supervised learning objective.
no code implementations • 31 Dec 2018 • Vasisht Duddu, Debasis Samanta, D. Vijay Rao, Valentina E. Balas
Deep learning is gaining importance in many applications.
no code implementations • 30 Mar 2018 • Vasisht Duddu, Debasis Samanta, D. Vijay Rao
Anonymous networks have enabled secure and anonymous communication between the users and service providers while maintaining their anonymity and privacy.
Cryptography and Security Networking and Internet Architecture