Hijack Vertical Federated Learning Models As One Party

Abstract

Vertical federated learning (VFL) is an emerging paradigm that enables collaborators to build machine learning models together in a distributed fashion. In general, these parties have a group of users in common but own different features. Existing VFL frameworks use cryptographic techniques to provide data privacy and security guarantees, leading to a line of works studying computing efficiency and fast implementation. However, the security of VFL's model remains underexplored.

arXiv commenthttps://doi.ieeecomputersociety.org/10.1109/TDSC.2024.3358081

References in corpus (16)

• Explaining and Harnessing Adversarial Examples
• mixup: Beyond Empirical Risk Minimization
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• How To Backdoor Federated Learning
• Federated Machine Learning: Concept and Applications
• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
• Can You Really Backdoor Federated Learning?
• Mitigating Sybils in Federated Learning Poisoning
• Learning to Detect Malicious Clients for Robust Federated Learning
• Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
• STRIP: A Defence Against Trojan Attacks on Deep Neural Networks
• Mitigating Backdoor Attacks in Federated Learning
• Private Machine Learning in TensorFlow using Secure Computation
• Backdoor attacks and defenses in feature-partitioned collaborative learning
• Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution
• Batch Label Inference and Replacement Attacks in Black-Boxed Vertical Federated Learning