Search Results for author:
Found 7 papers, 4 papers with code
Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Training
In addition, we present a SoK of the most recent PPML frameworks for model training and provide a comprehensive comparison in terms of the unique properties and performances on standard benchmarks.
GuardML: Efficient Privacy-Preserving Machine Learning Services Through Hybrid Homomorphic Encryption
Our work seeks to introduce HHE to ML by designing a PPML scheme tailored for end devices.
Love or Hate? Share or Split? Privacy-Preserving Training Using Split Learning and Homomorphic Encryption
In this setting, the client initially applies its part of the machine learning model on the raw data to generate activation maps and then sends them to the server to continue the training process.
Split Without a Leak: Reducing Privacy Leakage in Split Learning
The idea behind it is that the client encrypts the activation map (the output of the split layer between the client and the server) before sending it to the server.
Split Ways: Privacy-Preserving Training of Encrypted Data Using Split Learning
In this setting, the client initially applies its part of the machine learning model on the raw data to generate activation maps and then sends them to the server to continue the training process.
Temporal Sub-sampling of Audio Feature Sequences for Automated Audio Captioning
In this work we present an approach that focuses on explicitly taking advantage of this difference of lengths between sequences, by applying a temporal sub-sampling to the audio input sequence.
UIT-DANGNT-CLNLP at SemEval-2017 Task 9: Building Scientific Concept Fixing Patterns for Improving CAMR
This paper describes the improvements that we have applied on CAMR baseline parser (Wang et al., 2016) at Task 8 of SemEval-2016.
