2020

Threats to Federated Learning: A Survey

Lyu, Lingjuan, Yu, Han, Yang, Qiang

Understand

With the emergence of data silos and popular privacy awareness, the traditional centralized approach of training artificial intelligence (AI) models is facing strong challenges.

Federated learning (FL) has recently emerged as a promising solution under this new reality.
Existing FL protocol design has been shown to exhibit vulnerabilities which can be exploited by adversaries both within and without the system to compromise data privacy.
It is thus of paramount importance to make FL system designers to be aware of the implications of future FL algorithm design on privacy-preservation.

Built on

Privacy preserving association rule mining in vertically partitioned data
Jaideep Vaidya and Chris Clifton · 2002
Earlier work this paper cites.
Privacy-preserving distributed mining of association rules on horizontally partitioned data
Murat Kantarcioglu and Chris Clifton · 2004
Earlier work this paper cites.
Can machine learning be secure?
Marco Barreno, Blaine Nelson, Russell Sears, Anthony D Joseph, and J Doug Tygar · 2006
Earlier work this paper cites.
Support vector machines under adversarial label noise
Battista Biggio, Blaine Nelson, and Pavel Laskov · 2011
Earlier work this paper cites.
Adversarial machine learning
Ling Huang, Anthony D Joseph, Blaine Nelson, Benjamin IP Rubinstein, and J Doug Tygar · 2011
Earlier work this paper cites.
Poisoning attacks against support vector machines
Original
Battista Biggio, Blaine Nelson, and Pavel Laskov · 2012
Earlier work this paper cites.
Intriguing properties of neural networks
Original
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus · 2013
Earlier work this paper cites.
Model inversion attacks that exploit confidence information and basic countermeasures
Matt Fredrikson, Somesh Jha, and Thomas Ristenpart · 2015
Earlier work this paper cites.
Deep learning with differential privacy
Martín Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang · 2016
Earlier work this paper cites.
Communication-efficient learning of deep networks from decentralized data
Original
H Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, et al · 2016
Earlier work this paper cites.
Federated learning of deep networks using model averaging
Original
H Brendan McMahan, Eider Moore, Daniel Ramage, and Blaise Aguera y Arcas · 2016
Earlier work this paper cites.
Machine learning with adversaries: Byzantine tolerant gradient descent
Peva Blanchard, Rachid Guerraoui, Julien Stainer, et al · 2017
Earlier work this paper cites.
Practical secure aggregation for privacy-preserving machine learning
Keith Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth · 2017
Earlier work this paper cites.
Distributed statistical machine learning in adversarial settings: Byzantine gradient descent
Yudong Chen, Lili Su, and Jiaming Xu · 2017
Earlier work this paper cites.
Badnets: Identifying vulnerabilities in the machine learning model supply chain
Original
Tianyu Gu, Brendan Dolan-Gavitt, and Siddharth Garg · 2017
Earlier work this paper cites.

Similar

Deep models under the gan: information leakage from collaborative deep learning
Briland Hitaj, Giuseppe Ateniese, and Fernando Pérez-Cruz · 2017
Cited alongside, same era.
Membership inference attacks against machine learning models
Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov · 2017
Cited alongside, same era.
cpsgd: Communication-efficient and differentially-private distributed sgd
Naman Agarwal, Ananda Theertha Suresh, Felix Xinnan X Yu, Sanjiv Kumar, and Brendan McMahan · 2018
Cited alongside, same era.
Privacy-preserving deep learning via additively homomorphic encryption
Yoshinori Aono, Takuya Hayashi, Lihua Wang, Shiho Moriai, et al · 2018
Cited alongside, same era.
How to backdoor federated learning
Original
Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, and Vitaly Shmatikov · 2018
Cited alongside, same era.
signsgd with majority vote is communication efficient and fault tolerant
Original
Jeremy Bernstein, Jiawei Zhao, Kamyar Azizzadenesheli, and Anima Anandkumar · 2018
Cited alongside, same era.
Analyzing federated learning through an adversarial lens
Original
Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal, and Seraphin Calo · 2018
Cited alongside, same era.
Protection against reconstruction and its applications in private federated learning
Original
Abhishek Bhowmick, John Duchi, Julien Freudiger, Gaurav Kapoor, and Ryan Rogers · 2018
Cited alongside, same era.
Draco: Byzantine-resilient distributed training via redundant gradients
Original
Lingjiao Chen, Hongyi Wang, Zachary Charles, and Dimitris Papailiopoulos · 2018
Cited alongside, same era.
Mitigating sybils in federated learning poisoning
Original
Clement Fung, Chris JM Yoon, and Ivan Beschastnikh · 2018
Cited alongside, same era.
Learning iot in edge: Deep learning for the internet of things with edge computing
He Li, Kaoru Ota, and Mianxiong Dong · 2018
Cited alongside, same era.
Learning differentially private recurrent language models
H Brendan McMahan, Daniel Ramage, Kunal Talwar, and Li Zhang · 2018
Cited alongside, same era.

Then

Securing distributed machine learning in high dimensions
Original
Lili Su and Jiaming Xu · 2018
Later among the works it cites.
Byzantine-robust distributed learning: Towards optimal statistical rates
Original
Dong Yin, Yudong Chen, Kannan Ramchandran, and Peter Bartlett · 2018
Later among the works it cites.
Cronus: Robust and heterogeneous collaborative learning with black-box knowledge transfer
Original
Hongyan Chang, Virat Shejwalkar, Reza Shokri, and Amir Houmansadr · 2019
Later among the works it cites.
Privacy-preserving heterogeneous federated transfer learning
Dashan Gao, Yang Liu, Anbu Huang, Ce Ju, Han Yu, and Qiang Yang · 2019
Later among the works it cites.
Advances and open problems in federated learning
Original
Peter Kairouz, H Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al · 2019
Later among the works it cites.
Federated learning: Challenges, methods, and future directions
Original
Tian Li, Anit Kumar Sahu, Ameet Talwalkar, and Virginia Smith · 2019
Later among the works it cites.
Towards fair and decentralized privacy-preserving deep learning with blockchain
Original
Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar, Yitong Li, Xingjun Ma, and Jiong Jin · 2019
Later among the works it cites.
Exploiting unintended feature leakage in collaborative learning
Luca Melis, Congzheng Song, Emiliano De Cristofaro, and Vitaly Shmatikov · 2019
Later among the works it cites.
Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning
Milad Nasr, Reza Shokri, and Amir Houmansadr · 2019
Later among the works it cites.
Federated machine learning: Concept and applications
Qiang Yang, Yang Liu, Tianjian Chen, and Yongxin Tong · 2019
Later among the works it cites.
Federated Learning
Qiang Yang, Yang Liu, Yong Cheng, Yan Kang, Tianjian Chen, and Han Yu · 2019
Later among the works it cites.
Deep leakage from gradients
Ligeng Zhu, Zhijian Liu, and Song Han · 2019
Later among the works it cites.
Fedvision: An online visual object detection platform powered by federated learning
Yang Liu, Anbu Huang, Yun Luo, He Huang, Youzhi Liu, Yuanyuan Chen, Lican Feng, Tianjian Chen, Han Yu, and Qiang Yang · 2020
Closest in time.
idlg: Improved deep leakage from gradients
Original
Bo Zhao, Konda Reddy Mopuri, and Hakan Bilen · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…