A survey of recent advances in edge-computing-powered artificial intelligence of things

Z Chang, S Liu, X **_Federated_Learning_Security_from_a_Defenders_Perspective_A_Unified_CVPR_2024_paper.pdf" data-clk="hl=uk&sa=T&oi=gga&ct=gga&cd=2&d=13011345634947742228&ei=Cme9Z5GXOpeY6rQPksnM8AE" data-clk-atid="FLrj_OqVkbQJ" target="_blank">[PDF] thecvf.com

Revam** Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space

KN Kumar, R Mitra, CK Mohan - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Federated Learning (FL) facilitates clients to collaborate on training a shared machine
learning model without exposing individual private data. Nonetheless FL remains …

Ressfl: A resistance transfer framework for defending model inversion attack in split federated learning

J Li, AS Rakin, X Chen, Z He, D Fan… - Proceedings of the …, 2022 - openaccess.thecvf.com
This work aims to tackle Model Inversion (MI) attack on Split Federated Learning (SFL). SFL
is a recent distributed training scheme where multiple clients send intermediate activations …

Split learning with differential privacy for integrated terrestrial and non-terrestrial networks

M Wu, G Cheng, P Li, R Yu, Y Wu… - IEEE Wireless …, 2023 - ieeexplore.ieee.org
Integrated terrestrial and non-terrestrial networks (TNTNs) have become a promising
architecture for enabling ubiquitous connectivity. Smart remote sensing is one of the typical …

Aegis: Mitigating targeted bit-flip attacks against deep neural networks

J Wang, Z Zhang, M Wang, H Qiu, T Zhang… - 32nd USENIX Security …, 2023 - usenix.org
Bit-flip attacks (BFAs) have attracted substantial attention recently, in which an adversary
could tamper with a small number of model parameter bits to break the integrity of DNNs. To …

Rve-pfl: Robust variational encoder-based personalised federated learning against model inversion attacks

W Issa, N Moustafa, B Turnbull… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Federated learning (FL) enables distributed joint training of machine learning (ML) models
without the need to share local data. FL is, however, not immune to privacy threats such as …

Actionbert: Leveraging user actions for semantic understanding of user interfaces

Z He, S Sunkara, X Zang, Y Xu, L Liu… - Proceedings of the …, 2021 - ojs.aaai.org
As mobile devices are becoming ubiquitous, regularly interacting with a variety of user
interfaces (UIs) is a common aspect of daily life for many people. To improve the …

Towards practical secure neural network inference: the journey so far and the road ahead

ZÁ Mann, C Weinert, D Chabal, JW Bos - ACM Computing Surveys, 2023 - dl.acm.org
Neural networks (NNs) have become one of the most important tools for artificial
intelligence. Well-designed and trained NNs can perform inference (eg, make decisions or …

Anonymous and efficient authentication scheme for privacy-preserving distributed learning

Y Jiang, K Zhang, Y Qian, L Zhou - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Distributed learning is proposed as a promising technique to reduce heavy data
transmissions in centralized machine learning. By allowing the participants training the …