Search Results for author:
Found 32 papers, 6 papers with code
Differentially Private CutMix for Split Learning with Vision Transformer
Split learning (SL) detours this by communicating smashed data at a cut-layer, yet suffers from data privacy leakage and large communication costs caused by high similarity between ViT' s smashed data and input data.
Differentially Private Fréchet Mean on the Manifold of Symmetric Positive Definite (SPD) Matrices with log-Euclidean Metric
In that spirit, the only geometric statistical query for which a differential privacy mechanism has been developed, so far, is for the release of the sample Fr\'echet mean: the \emph{Riemannian Laplace mechanism} was recently proposed to privatize the Fr\'echet mean on complete Riemannian manifolds.
Private independence testing across two parties
We introduce $\pi$-test, a privacy-preserving algorithm for testing statistical independence between data distributed across multiple parties.
Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning
Leveraging this, we develop a novel SL framework for ViT, coined CutMixSL, communicating CutSmashed data.
Decouple-and-Sample: Protecting sensitive information in task agnostic data release
While releasing datasets continues to make a big impact in various applications of computer vision, its impact is mostly realized when data sharing is not inhibited by privacy concerns.
Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning
In recent years, there have been great advances in the field of decentralized learning with private data.
AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning
In this work, we introduce AdaSplit which enables efficiently scaling SL to low resource scenarios by reducing bandwidth consumption and improving performance across heterogeneous clients.
Private measurement of nonlinear correlations between data hosted across multiple parties
We introduce a differentially private method to measure nonlinear correlations between sensitive data hosted across two entities.
Sanitizer: Sanitizing data for anonymizing sensitive information
This is done in a two-step process: first, we develop a method that encodes unstructured image-like modality into a structured representation bifurcated by sensitive and non-sensitive representation.
Parallel Quasi-concave set optimization: A new frontier that scales without needing submodularity
We provide a parallel algorithm with a time complexity over $n$ processors of $\mathcal{O}(n^2g) +\mathcal{O}(\log{\log{n}})$ where $n$ is the cardinality of the ground set and $g$ is the complexity to compute the monotone linkage function that induces a corresponding quasi-concave set function via a duality.
AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning
In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and superpositioned samples.
PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval
1) We present a novel differentially private method \textit{PrivateMail} for supervised manifold learning, the first of its kind to our knowledge.
DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks
Recent deep learning models have shown remarkable performance in image classification.
NoPeek: Information leakage reduction to share activations in distributed deep learning
For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while maintaining model accuracy.
SplitNN-driven Vertical Partitioning
In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features.
FedML: A Research Library and Benchmark for Federated Machine Learning
Federated learning (FL) is a rapidly growing research field in machine learning.
Splintering with distributions: A stochastic decoy scheme for private computation
Performing computations while maintaining privacy is an important problem in todays distributed machine learning solutions.
Privacy in Deep Learning: A Survey
In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues.
Apps Gone Rogue: Maintaining Personal Privacy in an Epidemic
Containment, the key strategy in quickly halting an epidemic, requires rapid identification and quarantine of the infected individuals, determination of whom they have had close contact with in the previous days and weeks, and decontamination of locations the infected individual has visited.
Cryptography and Security Computers and Society Distributed, Parallel, and Cluster Computing
Split Learning for collaborative deep learning in healthcare
Shortage of labeled data has been holding the surge of deep learning in healthcare back, as sample sizes are often small, patient information cannot be shared openly, and multi-center collaborative studies are a burden to set up.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations
Recently, there has been the development of Split Learning, a framework for distributed computation where model components are split between the client and server (Vepakomma et al., 2018b).
ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
In this work we introduce ExpertMatcher, a method for automating deep learning model selection using autoencoders.
Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest
In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection.
Detailed comparison of communication efficiency of split learning and federated learning
We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning.
Data Markets to support AI for All: Pricing, Valuation and Governance
We discuss a data market technique based on intrinsic (relevance and uniqueness) as well as extrinsic value (influenced by supply and demand) of data.
No Peek: A Survey of private distributed deep learning
We survey distributed deep learning models for training or inference without accessing raw data from clients.
A Review of Homomorphic Encryption Libraries for Secure Computation
In this paper we provide a survey of various libraries for homomorphic encryption.
Cryptography and Security
Split learning for health: Distributed deep learning without sharing raw patient data
Can health entities collaboratively train deep learning models without sharing sensitive raw data?
Optimal bandwidth estimation for a fast manifold learning algorithm to detect circular structure in high-dimensional data
We provide a way to infer about existence of topological circularity in high-dimensional data sets in $\mathbb{R}^d$ from its projection in $\mathbb{R}^2$ obtained through a fast manifold learning map as a function of the high-dimensional dataset $\mathbb{X}$ and a particular choice of a positive real $\sigma$ known as bandwidth parameter.
Supervised Dimensionality Reduction via Distance Correlation Maximization
In our work, we propose a novel formulation for supervised dimensionality reduction based on a nonlinear dependency criterion called Statistical Distance Correlation, Szekely et.
DISCOMAX: A Proximity-Preserving Distance Correlation Maximization Algorithm
Our setting is different from subset-selection algorithms where the problem is to choose the best subset of features for regression.
