Robust Federated Learning with Attack-Adaptive Aggregation
arXiv:2102.05257
Abstract
Federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks, even if some existing defense strategies are used. To address this challenge, we propose an attack-adaptive aggregation strategy to defend against various attacks for robust federated learning. The proposed approach is based on training a neural network with an attention mechanism that learns the vulnerability of federated learning models from a set of plausible attacks. To the best of our knowledge, our aggregation strategy is the first one that can be adapted to defend against various attacks in a data-driven fashion. Our approach has achieved competitive performance in defending model poisoning and backdoor attacks in federated learning tasks on image and text datasets.
arXiv comment14 pages, submitted to FTL-IJCAI'21
References in corpus (24)
- Conditional Generative Adversarial Nets
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- On Calibration of Modern Neural Networks
- Federated Learning for Mobile Keyboard Prediction
- Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
- Robust Aggregation for Federated Learning
- How To Backdoor Federated Learning
- Poisoning Attacks against Support Vector Machines
- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
- Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
- The Hidden Vulnerability of Distributed Learning in Byzantium
- Differentially Private Federated Learning: A Client Level Perspective
- Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
- Can You Really Backdoor Federated Learning?
- Mitigating Sybils in Federated Learning Poisoning
- Protection Against Reconstruction and Its Applications in Private Federated Learning
- Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
- Learning to Detect Malicious Clients for Robust Federated Learning
- Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging
- Distilled One-Shot Federated Learning
- Attack-Resistant Federated Learning with Residual-based Reweighting
- A Little Is Enough: Circumventing Defenses For Distributed Learning
- Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
- A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks