Search Results for author:
Found 11 papers, 3 papers with code
Privacy-Preserving Algorithmic Recourse
We observe that PrivRecourse can provide paths that are private and realistic.
SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features
While any method to compute SHAP values with uncertainty estimates (such as KernelSHAP and SamplingSHAP) can be trivially adapted to solve TkIP, doing so is highly sample inefficient.
Information Flow Control in Machine Learning through Modular Model Architecture
In today's machine learning (ML) models, any part of the training data can affect its output.
Measuring and Controlling Split Layer Privacy Leakage Using Fisher Information
Split learning and inference propose to run training/inference of a large model that is split across client devices and the cloud.
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysis
Federated learning (FL) aims to perform privacy-preserving machine learning on distributed data held by multiple data owners.
ExPLoit: Extracting Private Labels in Split Learning
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
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
EDM is made up of models that are trained to produce dissimilar predictions for OOD inputs.
MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation
The effectiveness of such attacks relies heavily on the availability of data necessary to query the target model.
Defending Against Model Stealing Attacks with Adaptive Misinformation
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 a target model, just by using black-box query access.
Improving Adversarial Robustness of Ensembles with Diversity Training
Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked.
