Fetching the paper…
Reading the bibliography…
Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol.
How to share a secret
1979
Earlier work this paper cites.
Efficient identification and signatures for smart cards
1990
Earlier work this paper cites.
Non-interactive and information-theoretic secure verifiable secret sharing
1992
Earlier work this paper cites.
Gradient-based learning applied to document recognition
1998
Earlier work this paper cites.
On-line learning in neural networks
1999
Earlier work this paper cites.
Practical byzantine fault tolerance
1999
Earlier work this paper cites.
Verifiable random functions
1999
Earlier work this paper cites.
Exploiting Machine Learning to Subvert Your Spam Filter
2008
Earlier work this paper cites.
ANTIDOTE: Understanding and Defending Against Poisoning of Anomaly Detectors
2009
Earlier work this paper cites.
The Security of Machine Learning
2010
Earlier work this paper cites.
Large-Scale Machine Learning with Stochastic Gradient Descent
2010
Earlier work this paper cites.
Adversarial Machine Learning
2011
Earlier work this paper cites.
Hogwild: A lock-free approach to parallelizing stochastic gradient descent
2011
Earlier work this paper cites.
Poisoning Attacks Against Support Vector Machines
2012
Earlier work this paper cites.
Large scale distributed deep networks
2012
Earlier work this paper cites.
The Algorithmic Foundations of Differential Privacy
2014
Earlier work this paper cites.
Permacoin: Repurposing bitcoin work for data preservation
2014
Cited alongside, same era.
Model Inversion Attacks That Exploit Confidence Information and Basic Countermeasures
2015
Cited alongside, same era.
Privacy-preserving deep learning
2015
Cited alongside, same era.
Strength in numbers: Robust tamper detection in crowd computations
2015
Cited alongside, same era.
Deep learning with differential privacy
2016
Cited alongside, same era.
Federated learning: Strategies for improving communication efficiency
2016
Cited alongside, same era.
Auror: Defending against poisoning attacks in collaborative deep learning systems
Communication-Efficient Learning of Deep Networks from Decentralized Data
2017
Later among the works it cites.
Secureml: A system for scalable privacy-preserving machine learning, 2017
2017
Later among the works it cites.
Towards poisoning of deep learning algorithms with back-gradient optimization
2017
Later among the works it cites.
Automatic differentiation in pytorch
2017
Later among the works it cites.
Membership inference attacks against machine learning models
2017
Later among the works it cites.
https://github.com/coniks-sys/coniks-go
A CONIKS Implementation in Golang · 2018
Closest in time.
https://github.com/dedis/kyber
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
2016
Cited alongside, same era.
Defending against sybil devices in crowdsourced mapping services
2016
Cited alongside, same era.
Mitigating poisoning attacks on machine learning models: A data provenance based approach
2017
Cited alongside, same era.
Machine learning with adversaries: Byzantine tolerant gradient descent
2017
Cited alongside, same era.
Practical secure aggregation for privacy-preserving machine learning
2017
Cited alongside, same era.
UCI machine learning repository, 2017
2017
Cited alongside, same era.
DEDIS Advanced Crypto Library for Go · 2018
Closest in time.
https://github.com/sbinet/go-python
go-python · 2018
Closest in time.
How To Backdoor Federated Learning
2018
Closest in time.
Ekiden: A platform for confidentiality-preserving, trustworthy, and performant smart contract execution
2018
Closest in time.
Manipulating machine learning: Poisoning attacks and countermeasures for regression learning
2018
Closest in time.
Simple schnorr multi-signatures with applications to bitcoin
2018
Closest in time.
Inference Attacks Against Collaborative Learning
2018
Closest in time.
zkledger: Privacy-preserving auditing for distributed ledgers
2018
Closest in time.
Foreshadow: Extracting the keys to the Intel SGX kingdom with transient out-of-order execution
2018
Closest in time.
Analyzing federated learning through an adversarial lens
2019
Closest in time.