From accuracy to approximation: A survey on approximate homomorphic encryption and its applications

W Liu, L You, Y Shao, X Shen, G Hu, J Shi… - Computer Science …, 2025 - Elsevier
Due to the increasing popularity of application scenarios such as cloud computing, and the
growing concern of users about the security and privacy of their data, information security …

Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review

U Khan, U Nawaz, A Qayyum, S Ashraf, M Bilal… - arxiv preprint arxiv …, 2025 - arxiv.org
Recent advancements in machine learning (ML) and deep learning (DL), particularly
through the introduction of foundational models (FMs), have significantly enhanced surgical …

DReP: Deep ReLU pruning for fast private inference

P Hu, L Sun, C Hu, L Dai, S Guo, M Yu - Journal of Systems Architecture, 2024 - Elsevier
With increasing concerns about privacy issues in deep learning, privacy-preserving neural
network inference has been receiving growing attention from the community, but the …

Advances and Challenges in Privacy-Preserving Machine Learning

S Acheme, GN Edegbe… - 2024 IEEE …, 2024 - ieeexplore.ieee.org
Traditional machine learning relies on collecting data in a centralized location for training
algorithms, this raises privacy concerns, especially when using sensitive information like …

You Only Look Once in Panorama: Object Detection for 360 Videos with MLaaS

L Shen, M Zhang, C Zhang, J Liu - Proceedings of the 34th edition of the …, 2024 - dl.acm.org
360° videos are gaining popularity, but immersive analytics, particularly in object detection,
confront challenges from complex scenes and high data volume. This imposes significant …

A Systematic Review of Centralized and Decentralized Machine Learning Models: Security Concerns, Defenses and Future Directions

A Samuel, GN Edegbe - NIPES-Journal of Science and …, 2024 - journals.nipes.org
Abstract Models are the heart of machine learning as they represent the end product of the
learning process and help in making predictions. With the widespread adoption of machine …