arXiv (Cornell University) · 2019 · 47 citations · 22 references
ComputingComputer ScienceCybersecurityComputer SecurityDistributed SystemsMachine LearningAdversary TacticsAdversary TechniquesDeep LearningDistributed ComputingDistributed LearningNeural NetworksAdversarial RobustnessDistributed Machine LearningModel Accuracy AssessmentSecure Machine Learning
Distributed learning is central for large-scale training of deep-learning models. However, they are exposed to a security threat in which Byzantine participants can interrupt or control the learning process. Previous attack models and their corresponding defenses assume that the rogue participants are (a) omniscient (know the data of all other participants), and (b) introduce large change to the parameters. We show that small but well-crafted changes are sufficient, leading to a novel non-omniscient attack on distributed learning that go undetected by all existing defenses. We demonstrate our attack method works not only for preventing convergence but also for repurposing of the model behavior (backdooring). We show that 20% of corrupt workers are sufficient to degrade a CIFAR10 model accuracy by 50%, as well as to introduce backdoors into MNIST and CIFAR10 models without hurting their accuracy
22
Communication-Efficient Learning of Deep Networks from Decentralized Data
H. Brendan McMahan, Eider Moore, Daniel Ramage et al. · arXiv (Cornell University) · 2016 · 5.2K citations · Full text
Federated Learning: Strategies for Improving Communication Efficiency
Jakub Konečný, H. Brendan McMahan, Felix X. Yu et al. · arXiv (Cornell University) · 2016 · 3K citations · Full text
Trojaning Attack on Neural Networks
Yingqi Liu, Shiqing Ma, Yousra Aafer et al. · 2018 · 1.2K citations · Full text
Scaling distributed machine learning with the parameter server
Mu Li, David G. Andersen, Jun Woo Park et al. · Operating Systems Design and Implementation · 2014 · 1.1K citations