IEEE Transactions on Information Forensics and Security · 2024 · 10 citations · 17 references
ComputingComputer ScienceCybersecurityComputer SecurityMachine LearningNeural EngineeringAdversary TechniquesDeep LearningFederated LearningNeural NetworksOptimization For Machine LearningSurrogate-assisted OptimizationAdversarial RobustnessAdversary ModelAttack MitigationData Poisoning AttacksMachine-learning AttacksOptimal TransportVisibility
Federated learning (FL) has emerged as a powerful collaborative learning approach that enables client devices to train a joint machine learning model without sharing private data. However, the decentralized nature of FL makes it highly vulnerable to adversarial attacks from multiple sources. There are diverse FL data poisoning and model poisoning attack methods in the literature. Nevertheless, most of them focus only on the attack’s impact and do not consider the attack budget and attack visibility. These factors are essential to effectively comprehend the adversary’s rationale in designing an attack. Hence, our work highlights the significance of considering these factors by providing an attacker perspective in designing an attack with a low budget, low visibility, and high impact. Also, existing attacks that use total neuron replacement and randomly selected neuron replacement approaches only cater to these factors partially. Therefore, we propose a novel federated learning minimal model replacement attack (FL-MMR) that uses optimal transport (OT) for minimal neural alignment between a surrogate poisoned model and the benign model. Later, we optimize the attack budget in a three-fold adaptive fashion by considering critical learning periods and introducing the replacement map. In addition, we comprehensively evaluate our attack under three threat scenarios using three large-scale datasets: GTSRB, CIFAR10, and EMNIST. We observed that our FL-MMR attack drops global accuracy to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\approx 35\%$ </tex-math></inline-formula> less with merely 0.54% total attack budget and lower attack visibility than other attacks. The results confirm that our method aligns closely with the attacker’s viewpoint compared to other methods.
17
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
EMNIST: Extending MNIST to handwritten letters
Gregory Cohen, Saeed Afshar, Jonathan Tapson et al. · 2017 · 1.6K citations
The German Traffic Sign Recognition Benchmark: A multi-class classification competition
Johannes Stallkamp, Marc Schlipsing, Jan Salmen et al. · 2011 · 1.1K citations
FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping
Xiaoyu Cao, Minghong Fang, Jia Liu et al. · 2021 · 790 citations · Full text
On the Translocation of Masses
L. V. Kantorovich · Journal of Mathematical Sciences · 2006 · 764 citations · Full text