Securing SIFT: Privacy-Preserving Outsourcing Computation of Feature Extractions Over Encrypted Image Data

Abstract

Advances in cloud computing have greatly motivated data owners to outsource their huge amount of personal multimedia data and/or computationally expensive tasks onto the cloud by leveraging its abundant resources for cost saving and flexibility. Despite the tremendous benefits, the outsourced multimedia data and its originated applications may reveal the data owner's private information, such as the personal identity, locations, or even financial profiles. This observation has recently aroused new research interest on privacy-preserving computations over outsourced multimedia data. In this paper, we propose an effective and practical privacy-preserving computation outsourcing protocol for the prevailing scale-invariant feature transform (SIFT) over massive encrypted image data. We first show that the previous solutions to this problem have either efficiency/security or practicality issues, and none can well preserve the important characteristics of the original SIFT in terms of distinctiveness and robustness. We then present a new scheme design that achieves efficiency and security requirements simultaneously with the preservation of its key characteristics, by randomly splitting the original image data, designing two novel efficient protocols for secure multiplication and comparison, and carefully distributing the feature extraction computations onto two independent cloud servers. We both carefully analyze and extensively evaluate the security and effectiveness of our design. The results show that our solution is practically secure, outperforms the state-of-the-art, and performs comparably with the original SIFT in terms of various characteristics, including rotation invariance, image scale invariance, robust matching across affine distortion, and addition of noise and change in 3D viewpoint and illumination.

A Lightweight Fine-Grained Search Scheme over Encrypted Data in Cloud-Assisted Wireless Body Area Networks

“…Nevertheless, the keyword search functionality is not provided in existing ABE schemes. Motivated by the idea of providing the flexible data search and data share, Zheng et al [13] introduced two attribute based keyword search (ABKS) schemes, i.e., key policy ABKS (KP-ABKS) and ciphertext policy ABKS (CP-ABKS), by combining the conceptions of SE and ABE together. For the WBANs, CP-ABKS is more suitable than KP-ABKS since data owners are permitted to independently designate access policies themselves to determine who can flexibly search and access the encrypted medical data.…”

“…Although much attention in SE technology has been attracted in both academical and industrial fields, it is still unsuitable for WBANs as patients commonly desire that their medical data could be shareable and accessible by different data users (e.g., government agencies, healthcare providers, medical researchers, and insurance underwriters). To furnish access control with fine-granularity over medical data in SE solutions, ciphertext policy attribute based keyword search (CP-ABKS) is proposed [13,14]. In a CP-ABKS scheme, data users can decipher the ciphertexts of interest on the premise that the attributes match the access policy attached to the ciphertexts and meanwhile the submitted trapdoors satisfy the keyword indexes.…”

Augmenting Encrypted Search: A Decentralized Service Realization with Enforced Execution

“…In most existing works, the remote server is modeled as an honest-but-curious entity [7], [8], [9], [10], [11], [12], [13], [14], [15] who never tries to deviate from the prescribed protocol. In reality, however, a malicious server may return partial answers or even non-matching documents (e.g., due to random failures).…”

Design for a Image Processing Virtual Simulation Platform

“…This paper constructs a image processing virtual simulation platform based on MATLAB GUI. The platform has five modules, which integrate basic function (rotation, brighten, graying, zooming, and restoration), noise adding (impulse noise, Gaussian noise, and multiple noise), image denoising [2] (median filter and linear filter), feature extraction [3] (susan,harris and sift [4] feature detection), and image mosaic [5] functions. We conduct the platform main interface based on M language.…”