NoPeek: Information leakage reduction to share activations in distributed deep learning
By Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, Ramesh Raskar. 2020
119 citations recorded by the source corpus.
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. Leakage (measured using distance correlation between input and intermediate representations) is the risk associated with the invertibility of raw data from intermediary representations. This can prevent client entities that hold sensitive data from using distributed deep learning services. We demonstrate that our method is resilient to such reconstruction attacks and is based on reduction of distance correlation between raw data and learned representations during training and inference with image datasets. We prevent such reconstruction of raw data while maintaining information required to sustain good classification accuracies.
Subfields: Artificial Intelligence, 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 Artificial Intelligence
- Praneeth Vepakomma
- Abhishek Singh
- Ramesh Raskar
- Vivek Sharma
- Ethan Garza
- Emily Zhang
- Ayush Chopra
- Otkrist Gupta
In Federated & Distributed Learning
- Praneeth Vepakomma
- Vivek Sharma
- Abhishek Singh
- Ramesh Raskar
- Chaoyang He
- Murali Annavaram
- Otkrist Gupta
- Tristan Swedish
In Privacy & Security
Citations in the corpus
- DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks (2020, methodology): “Baselines For attacks on sensitive attributes, we baseline with ARL based methods [29, 24, 23] which are state-ofthe-art on attribute leakage.”