Federated Machine Learning: Concept and Applications
Citations
1,107 citations
895 citations
766 citations
Cites background from "Federated Machine Learning: Concept..."
...With data increasingly being generated on federated networks of remote devices, there is growing interest in empowering on-device applications with models that make use of such data [22, 23, 30, 19, 37]....
[...]
701 citations
606 citations
References
18,616 citations
"Federated Machine Learning: Concept..." refers methods in this paper
...In this case, transfer-learning [50] techniques can be applied to provide solutions for the entire sample and feature space under a federation (Figure 2(c))....
[...]
14,377 citations
"Federated Machine Learning: Concept..." refers background in this paper
...With AlphaGo [59] defeating the top humanGo players, we have trulywitnessed the huge potential in AI and have began to expectmore complex, cutting-edge AI technology in many applications, including driverless cars, medical care, and finance....
[...]
...With AlphaGo’s success, people naturally hope that the big data–driven AI such as AlphaGo will be realized soon in all aspects of our lives....
[...]
...The current public interest in AI is partly driven by Big Data availability: AlphaGo in 2016 used a total of 300,000 games as training data to achieve excellent results....
[...]
...With AlphaGo[59] defeating the top human Go players, we have truly witnessed the huge potential in artificial intelligence (AI), and have began to expect more complex, cutting-edge AI technology in many applications, including driverless cars, medical care, finance, etc....
[...]
7,925 citations
"Federated Machine Learning: Concept..." refers methods in this paper
...Another line of work uses the techniques differential privacy [18] or kanonymity [63] for data privacy protection [1, 12, 42, 61]....
[...]
3,579 citations
"Federated Machine Learning: Concept..." refers background or methods in this paper
...SMC provides formal privacy proof for these protocols [25]....
[...]
...The above architecture is proved to protect data leakage against the semihonest server if gradient aggregation is done with SMC [9] or homomorphic encryption [51]....
[...]
...These works all used SMC [25, 72] for privacy guarantees....
[...]
...Recently, a study [46] used the SMC framework for training machine-learning models with two servers and semi-honest assumptions....
[...]
...SMC securitymodels involvemultiple parties and provide security proof in a well-defined simulation framework to guarantee complete zero knowledge, that is, each party knows nothing except its input and output....
[...]
3,510 citations
"Federated Machine Learning: Concept..." refers methods in this paper
...SMC provides formal privacy proof for these protocols [25]....
[...]
...The above architecture is proved to protect data leakage against the semihonest server if gradient aggregation is done with SMC [9] or homomorphic encryption [51]....
[...]
...These works all used SMC [25, 72] for privacy guarantees....
[...]
...Recently, a study [46] used the SMC framework for training machine-learning models with two servers and semi-honest assumptions....
[...]
...SMC securitymodels involvemultiple parties and provide security proof in a well-defined simulation framework to guarantee complete zero knowledge, that is, each party knows nothing except its input and output....
[...]