no code implementations • 6 Mar 2024 • Tanveer Khan, Mindaugas Budzys, Khoa Nguyen, Antonis Michalas
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.
no code implementations • 26 Jan 2024 • Eugene Frimpong, Khoa Nguyen, Mindaugas Budzys, Tanveer Khan, Antonis Michalas
Our work seeks to introduce HHE to ML by designing a PPML scheme tailored for end devices.
2 code implementations • 19 Sep 2023 • Tanveer Khan, Khoa Nguyen, Antonis Michalas, Alexandros Bakas
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.
1 code implementation • 30 Aug 2023 • Khoa Nguyen, Tanveer Khan, Antonis Michalas
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.
1 code implementation • 20 Jan 2023 • Tanveer Khan, Khoa Nguyen, Antonis Michalas
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.
1 code implementation • 6 Jul 2020 • Khoa Nguyen, Konstantinos Drossos, Tuomas Virtanen
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.
no code implementations • SEMEVAL 2017 • Khoa Nguyen, Dang Nguyen
This paper describes the improvements that we have applied on CAMR baseline parser (Wang et al., 2016) at Task 8 of SemEval-2016.