AGGREGATHOR: Byzantine Machine Learning via Robust Gradient Aggregation

By Georgios Damaskinos, El-Mahdi El-Mhamdi, Rachid Guerraoui, Arsany Guirguis, Sébastien Rouault. 2019

96 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Attack of the Tails: Yes, You Really Can Backdoor Federated Learning (2020, background): “Using robust estimation to defend against byzantine attacks has been studied extensively [66, 67, 68, 69, 70, 24, 71].”
Salvaging Federated Learning by Local Adaptation (2020, methodology): “To limit the inﬂu-ence of individual participants, several robust, “Byzantine-tolerant” aggregation schemes have been proposed (Blan-chard et al., 2017; El Mhamdi et al., 2018; Damaskinos et al., 2019; Rajput et al., 2019; Chen et al., 2017).”
DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation (2019, methodology): “For the ﬁrst, robust aggregators are typically expensive to compute and scale super-linearly (in many cases quadratically [10, 4]) with the number of compute nodes.”
Privacy and Robustness in Federated Learning: Attacks and Defenses (2020, methodology): “Most existing robustness defenses are gradient aggregation methods initially developed for either privacy protection such as Secure Aggregation (SecAgg) [5] and participant-level differential privacy [7], [45], or Byzantine-tolerant learning such as Krum/Multi-Krum [13], AGGREGATHOR [46], Byzantine ”
Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications (2021, background): “…issue by keeping datasets locally, the shared model updates still cause extreme privacy leakage (e.g., model inversion attack), the learned global model can be colluded by malicious attackers [40], [165], and the edge devices may be adversarial at-tackers (e.g., data or model poisoning).”
Byzantine-Robust Learning on Heterogeneous Datasets via Resampling (2020, background): “There has been signiﬁcant recent work of the case when the workers have identical data distributions (Blanchard et al., 2017; Chen et al., 2017; Mhamdi et al., 2018; Alistarh et al., 2018; Mhamdi et al., 2018; Yin et al., 2018a,b; Su and Xu, 2018; Damaskinos et al., 2019).”
Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging (2019, methodology): “To mitigate this limitation, different robust federated learning strategies have already been proposed in the literature (Blanchard et al. 2017; Mhamdi, Guerraoui, and Rouault 2018; Yin et al. 2018; Damaskinos et al. 2019; Chen, Su, and Xu 2017; Chen et al. 2018; Xie, Koyejo, and Gupta 2019b).”
Fast and Secure Distributed Learning in High Dimension (2019, methodology): “least quadratic in dand hence impractical. A strength of MULTI-BULYAN is that it inherits the O(d) merits of both multi-Krum and Bulyan. *A practical implementation based on this work is described in [3], the code is available in the following Github repository: https://github.com/LPD-EPFL/AggregaTh”