98 citations · 111 across the 6 of their papers we have counts for
7 papers
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysis
Sanjay Kariyappa, Chuan Guo, Kiwan Maeng +4
Federated learning (FL) aims to perform privacy-preserving machine learning on distributed data held by multiple data owners. To this end, FL requires the data owners to perform tr…
ExPLoit: Extracting Private Labels in Split Learning
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…
Enabling Inference Privacy with Adaptive Noise Injection
Sanjay Kariyappa, Ousmane Dia, Moinuddin K Qureshi
User-facing software services are becoming increasingly reliant on remote servers to host Deep Neural Network (DNN) models, which perform inference tasks for the clients. Such serv…
MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation
Sanjay Kariyappa, Atul Prakash, Moinuddin Qureshi
Model Stealing (MS) attacks allow an adversary with black-box access to a Machine Learning model to replicate its functionality, compromising the confidentiality of the model. Such…
Defending Against Model Stealing Attacks with Adaptive Misinformation
Sanjay Kariyappa, Moinuddin K Qureshi
Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of…
Improving Adversarial Robustness of Ensembles with Diversity Training
Sanjay Kariyappa, Moinuddin K. Qureshi
Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the pr…
CRAM: Efficient Hardware-Based Memory Compression for Bandwidth Enhancement
Vinson Young, Sanjay Kariyappa, Moinuddin K. Qureshi
This paper investigates hardware-based memory compression designs to increase the memory bandwidth. When lines are compressible, the hardware can store multiple lines in a single m…