Backdoor attacks and defenses in feature-partitioned collaborative learning

Abstract

Since there are multiple parties in collaborative learning, malicious parties might manipulate the learning process for their own purposes through backdoor attacks. However, most of existing works only consider the federated learning scenario where data are partitioned by samples. The feature-partitioned learning can be another important scenario since in many real world applications, features are often distributed across different parties. Attacks and defenses in such scenario are especially challenging when the attackers have no labels and the defenders are not able to access the data and model parameters of other participants. In this paper, we show that even parties with no access to labels can successfully inject backdoor attacks, achieving high accuracy on both main and backdoor tasks. Next, we introduce several defense techniques, demonstrating that the backdoor can be successfully blocked by a combination of these techniques without hurting main task accuracy. To the best of our knowledge, this is the first systematical study to deal with backdoor attacks in the feature-partitioned collaborative learning framework.

to be published in FL-ICML 2020 workshop

References in corpus (9)

• Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• How To Backdoor Federated Learning
• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
• Can You Really Backdoor Federated Learning?
• SecureBoost: A Lossless Federated Learning Framework
• Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging
• A Communication Efficient Collaborative Learning Framework for Distributed Features
• Learning Privately over Distributed Features: An ADMM Sharing Approach

Cited by in corpus (7)

• Vertical Federated Learning: Concepts, Advances and Challenges
• FedML: A Research Library and Benchmark for Federated Machine Learning
• Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
• Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
• Hijack Vertical Federated Learning Models As One Party
• Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm
• An Exploratory Analysis on Users' Contributions in Federated Learning