DeepAI AI Chat
Log In Sign Up

Federated Learning in Adversarial Settings

by   Raouf Kerkouche, et al.

Federated Learning enables entities to collaboratively learn a shared prediction model while keeping their training data locally. It prevents data collection and aggregation and, therefore, mitigates the associated privacy risks. However, it still remains vulnerable to various security attacks where malicious participants aim at degrading the generated model, inserting backdoors, or inferring other participants' training data. This paper presents a new federated learning scheme that provides different trade-offs between robustness, privacy, bandwidth efficiency, and model accuracy. Our scheme uses biased quantization of model updates and hence is bandwidth efficient. It is also robust against state-of-the-art backdoor as well as model degradation attacks even when a large proportion of the participant nodes are malicious. We propose a practical differentially private extension of this scheme which protects the whole dataset of participating entities. We show that this extension performs as efficiently as the non-private but robust scheme, even with stringent privacy requirements but are less robust against model degradation and backdoor attacks. This suggests a possible fundamental trade-off between Differential Privacy and robustness.


page 1

page 2

page 3

page 4


Compression Boosts Differentially Private Federated Learning

Federated Learning allows distributed entities to train a common model c...

Constrained Differentially Private Federated Learning for Low-bandwidth Devices

Federated learning becomes a prominent approach when different entities ...

Towards Causal Federated Learning For Enhanced Robustness and Privacy

Federated Learning is an emerging privacy-preserving distributed machine...

Can collaborative learning be private, robust and scalable?

We investigate the effectiveness of combining differential privacy, mode...

Secure and Privacy-Preserving Federated Learning via Co-Utility

The decentralized nature of federated learning, that often leverages the...

The Skellam Mechanism for Differentially Private Federated Learning

We introduce the multi-dimensional Skellam mechanism, a discrete differe...

Simeon – Secure Federated Machine Learning Through Iterative Filtering

Federated learning enables a global machine learning model to be trained...