Search Results for author:
Found 6 papers, 2 papers with code
S-GBDT: Frugal Differentially Private Gradient Boosting Decision Trees
For the Abalone dataset for $\varepsilon=0. 54$ we achieve $R^2$-score of $0. 47$ which is very close to the $R^2$-score of $0. 54$ for the nonprivate version of GBDT.
DPM: Clustering Sensitive Data through Separation
Privacy-preserving clustering groups data points in an unsupervised manner whilst ensuring that sensitive information remains protected.
Distributed DP-Helmet: Scalable Differentially Private Non-interactive Averaging of Single Layers
We provide experimental evidence that blind averaging for SVMs and single Softmax-layer (Softmax-SLP) can have a strong utility-privacy tradeoff: we reach an accuracy of 86% on CIFAR-10 for $\varepsilon$ = 0. 4 and 1, 000 users, of 44% on CIFAR-100 for $\varepsilon$ = 1. 2 and 100 users, and of 39% on federated EMNIST for $\varepsilon$ = 0. 4 and 3, 400 users, all after a SimCLR-based pretraining.
Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms
An additive mechanism with truncated noise (i. e., with bounded range) can offer such hard bounds.
Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
This survey provides an overview of the technical and procedural challenges involved in creating medical machine learning systems responsibly and in conformity with existing regulations, as well as possible solutions to address these challenges.
Computational Soundness for Dalvik Bytecode
Second, we show that our abstractions are faithful by providing the first computational soundness result for Dalvik bytecode, i. e., the absence of attacks against our symbolically abstracted program entails the absence of any attacks against a suitable cryptographic program realization.
Cryptography and Security
