Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysis

no code implementations • 12 Sep 2022 • Sanjay Kariyappa, Chuan Guo, Kiwan Maeng, Wenjie Xiong, G. Edward Suh, Moinuddin K Qureshi, Hsien-Hsin S. Lee

Federated learning (FL) aims to perform privacy-preserving machine learning on distributed data held by multiple data owners.

blind source separation Federated Learning +1

ExPLoit: Extracting Private Labels in Split Learning

no code implementations • 25 Nov 2021 • Sanjay Kariyappa, Moinuddin K Qureshi

Split learning is a popular technique used for vertical federated learning (VFL), where the goal is to jointly train a model on the private input and label data held by two parties.

Image Classification Vertical Federated Learning

Enabling Inference Privacy with Adaptive Noise Injection

no code implementations • 6 Apr 2021 • Sanjay Kariyappa, Ousmane Dia, Moinuddin K Qureshi

To this end, we propose Adaptive Noise Injection (ANI), which uses a light-weight DNN on the client-side to inject noise to each input, before transmitting it to the service provider to perform inference.

Protecting DNNs from Theft using an Ensemble of Diverse Models

no code implementations • ICLR 2021 • Sanjay Kariyappa, Atul Prakash, Moinuddin K Qureshi

EDM is made up of models that are trained to produce dissimilar predictions for OOD inputs.

Image Classification