LGAICRMLNov 29, 2018

Analyzing Federated Learning through an Adversarial Lens

arXiv:1811.12470v41317 citations
Originality Incremental advance
AI Analysis

This highlights a critical security flaw in federated learning systems, which are widely used for privacy-preserving machine learning, necessitating the development of effective defenses.

The paper tackled the vulnerability of federated learning to model poisoning attacks by a single malicious agent, showing that such attacks can cause misclassification of chosen inputs with high confidence while maintaining stealth, as demonstrated through visual explanations that are nearly indistinguishable from benign models.

Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this work, we explore the threat of model poisoning attacks on federated learning initiated by a single, non-colluding malicious agent where the adversarial objective is to cause the model to misclassify a set of chosen inputs with high confidence. We explore a number of strategies to carry out this attack, starting with simple boosting of the malicious agent's update to overcome the effects of other agents' updates. To increase attack stealth, we propose an alternating minimization strategy, which alternately optimizes for the training loss and the adversarial objective. We follow up by using parameter estimation for the benign agents' updates to improve on attack success. Finally, we use a suite of interpretability techniques to generate visual explanations of model decisions for both benign and malicious models and show that the explanations are nearly visually indistinguishable. Our results indicate that even a highly constrained adversary can carry out model poisoning attacks while simultaneously maintaining stealth, thus highlighting the vulnerability of the federated learning setting and the need to develop effective defense strategies.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes