R EDUCING LEAKAGE IN DISTRIBUTED DEEP LEARNING FOR SENSITIVE HEALTH DATA

By Praneeth Vepakomma, Otkrist Gupta, Abhimanyu Dubey, Ramesh Raskar. 2019

Subfields: Federated & Distributed Learning, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Federated & Distributed Learning

In Privacy & Security

Citations in the corpus

Advances and Open Problems in Federated Learning (2019, background): “A variation of split learning called NoPeek SplitNN [395] reduces the potential leakage via communicated activations, by reducing their distance correlation [394, 378] with the raw data, while maintaining good model performance via categorical cross-entropy.”
SplitNN-driven Vertical Partitioning (2020, neutral): “…as STC (Sattler et al. , 2019) or Random Rotation Matrix (Koneˇcný et al. , 2017) as well as privacy preserving techniques such as Secure Aggregation Protocol (Bonawitz et al. , 2016) or minimizing Distance Correlation (Vepakomma et al. , 2019), as well as their effect on the computational cost.”
ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations (2019, methodology): “…and we experimentally show that we can achieve similar performance as Sharma et al. (2019) to match the task (coarseLevel) assignment and reasonably good performance for class (fine-grained) assignment in a Split Learning distributed computation framework (Vepakomma et al. , 2018b, 2019, 2018a).”
Detailed comparison of communication efficiency of split learning and federated learning (2019, background): “Federated learning (McMahan et al., 2016; Koneˇcn`y et al., 2016) and Split learning (Gupta & Raskar, 2018; Vepakomma et al., 2018, 2019) are two methods which allow to train a model collectively from various distributed data sources without sharing raw data.”
Wireless Network Intelligence at the Edge (2018, background): “More general model split-based edge ML frameworks are discussed in [206] and [207], in the context of health applications with private patient data.”
Federated Learning: Challenges, Methods, and Future Directions (2019, background): “Despite the fact that differential privacy is the de facto metric for privacy in machine learning, there are many other privacy definitions, such as k-anonymity [36], δ-presence [81] and distance correlation [117], that may be applicable to different learning problems [118].”
Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications (2020, background): “With these benefits, SL has recently been adopted in medical applications wherein dispersed private health records should be exploited without sharing raw data [21], [74], [78].”
SplitFed: When Federated Learning Meets Split Learning (2020, background): “This issue can be controlled by modifying the loss function at the clientside (Vepakomma et al. 2019).”
Self-supervised Cross-silo Federated Neural Architecture Search (2021, methodology): “Split Neural Network (SplitNN) [10], [11], [34]–[37] is another framework that can be employed for dealing with VFL problems.”
ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries (2019, methodology): “Thanks to modern cloud infrastructure and distributed learning methods (Vepakomma et al. , 2018b, 2019, 2018a; Chang et al. , 2018), “expert model hubs” can make inference available to any remote client connected to the internet.”
Communication-Efficient Multimodal Split Learning for mmWave Received Power Prediction (2020, methodology): “In [11], to improve privacy guarantees in SL, the split NN is optimized to maximize the KL divergence between the distributions of raw health data and NN activa-”