Privacy-Preserving near Neighbor Search via Sparse Coding with Ambiguation

Abstract

In this paper, we propose a framework for privacypreserving approximate near neighbor search via stochastic sparsifying encoding. The core of the framework relies on sparse coding with ambiguation (SCA) mechanism that introduces the notion of inherent shared secrecy based on the support intersection of sparse codes. This approach is 'fairness-aware', in the sense that any point in the neighborhood has an equiprobable chance to be chosen. Our approach can be applied to raw data, latent representation of autoencoders, and aggregated local descriptors. The proposed method is tested on both synthetic i.i.d data and real image databases.

A Theoretically Novel Trade-off for Sparse Secret-key Generation

“…A sparse dictionary learning problem can be mathematically formulated as [1], [2], [3], [4], [5], [6]…”

“…M Any machine learning and modern signal processing applications − such as bio-metric authentication/identification and recommending systems − , follow sparse signal processing techniques [1], [2], [3], [4], [5], [6]. The sparse synthesis model focuses on those data sets that can be approximated using a linear combination of only a small number of cells of a dictionary.…”

“…Something that is traditional as mentioned in the paper in the next parts 2. According to the Kerckchoffs's principle in cryptography[1].…”