Dropping Activation Outputs with Localized First-layer Deep Network for Enhancing User Privacy and Data Security

20 November 2017

Papers citing "Dropping Activation Outputs with Localized First-layer Deep Network for Enhancing User Privacy and Data Security"

6 / 6 papers shown

Title
HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning Pengyu Qiu Xuhong Zhang S. Ji Chong Fu Xing Yang Ting Wang FedML AAML 30 12 0 01 Dec 2022
Split Learning without Local Weight Sharing to Enhance Client-side Data Privacy Ngoc Duy Pham Tran Dang Khoa Phan A. Abuadbba Yansong Gao Doan Nguyen Naveen Chilamkurti 28 5 0 01 Dec 2022
MixNN: A design for protecting deep learning models Chao Liu Hao Chen Yusen Wu Rui Jin 10 0 0 28 Mar 2022
Demystifying Swarm Learning: A New Paradigm of Blockchain-based Decentralized Federated Learning Jialiang Han Y. Ma Yudong Han 43 15 0 14 Jan 2022
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,138 0 06 Jun 2015
Improving neural networks by preventing co-adaptation of feature detectors Geoffrey E. Hinton Nitish Srivastava A. Krizhevsky Ilya Sutskever Ruslan Salakhutdinov VLM 266 7,636 0 03 Jul 2012