research
∙
07/10/2023
SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features
The SHAP framework provides a principled method to explain the predictio...
share
research
∙
06/05/2023
Information Flow Control in Machine Learning through Modular Model Architecture
In today's machine learning (ML) models, any part of the training data c...
research
∙
05/06/2023
Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
Privacy-preserving instance encoding aims to encode raw data as feature ...
research
∙
09/21/2022
Measuring and Controlling Split Layer Privacy Leakage Using Fisher Information
Split learning and inference propose to run training/inference of a larg...
research
∙
09/12/2022
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysis
Federated learning (FL) aims to perform privacy-preserving machine learn...
research
∙
11/25/2021
Gradient Inversion Attack: Leaking Private Labels in Two-Party Split Learning
Split learning is a popular technique used to perform vertical federated...
research
∙
04/06/2021
Enabling Inference Privacy with Adaptive Noise Injection
User-facing software services are becoming increasingly reliant on remot...
research
∙
05/06/2020
MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation
Model Stealing (MS) attacks allow an adversary with black-box access to ...
research
∙
11/16/2019
Defending Against Model Stealing Attacks with Adaptive Misinformation
Deep Neural Networks (DNNs) are susceptible to model stealing attacks, w...
research
∙
01/28/2019
Improving Adversarial Robustness of Ensembles with Diversity Training
Deep Neural Networks are vulnerable to adversarial attacks even in setti...
research
∙
07/20/2018