Secure SURF with Fully Homomorphic Encryption
Cloud computing is an important part of today's world because offloading computations is a method to reduce costs. In this paper, we investigate computing the Speeded Up Robust Features (SURF) using Fully Homomorphic Encryption (FHE). Performing SURF in FHE enables a method to offload the computations while maintaining security and privacy of the original data. In support of this research, we developed a framework to compute SURF via a rational number based compatible with FHE. Although floating point (R) to rational numbers (Q) conversion introduces error, our research provides tight bounds on the magnitude of error in terms of parameters of FHE. We empirically verified the proposed method against a set of images at different sizes and showed that our framework accurately computes most of the SURF keypoints in FHE.
Code (0)
등록된 구현이 없습니다.
Tasks
Cloud ComputingSimilar Papers 제목 키워드 기반
I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
In today's machine learning landscape, fine-tuning pretrained transformer models has emerged as an essential technique, particularly in scenarios where access to task-aligned training data is limited. However, challenges…
image-classificationImage ClassificationPrivacy PreservingCipherFace: A Fully Homomorphic Encryption-Driven Framework for Secure Cloud-Based Facial Recognition
Facial recognition systems rely on embeddings to represent facial images and determine identity by verifying if the distance between embeddings is below a pre-tuned threshold. While embeddings are not reversible to origi…
Privacy-Preserving Chaotic Extreme Learning Machine with Fully Homomorphic Encryption
The Machine Learning and Deep Learning Models require a lot of data for the training process, and in some scenarios, there might be some sensitive data, such as customer information involved, which the organizations migh…
BIG-bench Machine LearningDeep LearningPrivacy PreservingMedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption
Advancements in machine learning (ML) have significantly revolutionized medical image analysis, prompting hospitals to rely on external ML services. However, the exchange of sensitive patient data, such as chest X-rays, …
Medical Image AnalysisPrivacy PreservingA review of homomorphic encryption and software tools for encrypted statistical machine learning
Recent advances in cryptography promise to enable secure statistical computation on encrypted data, whereby a limited set of operations can be carried out without the need to first decrypt. We review these homomorphic en…
BIG-bench Machine Learning