Transparent hashing in the encrypted domain for privacy preserving image retrieval

  title={Transparent hashing in the encrypted domain for privacy preserving image retrieval},
  author={Kannan Karthik and Sachin Kashyap},
  journal={Signal, Image and Video Processing},
Search through a database of encrypted images against a crumpled and encrypted query will remain privacy preserving only if comparisons between selective features derived from these images is executed in the encrypted domain itself. To facilitate this, the encryption process must remain transparent to specific image statistics computed in the spatial or transform domain. Consequently, the perceptual hash formed by quantizing the image statistics remains the same before and after the encryption… 
Secure content‐based image retrieval using modified Euclidean distance for encrypted features
In this article, a secure image retrieval scheme is proposed, which focuses on providing satisfactory retrieval results, and the framework searches relevant images even in an encrypted domain without
A Secure JPEG Image Retrieval Method in Cloud Environment
Experimental results prove that the proposed secure JPEG image retrieval method has good encryption security and can achieve better retrieval performance.
A Privacy-preserving Image Retrieval Method Based on Improved BoVW Model in Cloud Environment
An improved BoVW method based on Hamming embedding can provide binary signatures that refine the matching based on visual words; therefore, retrieval precision is improved significantly and orthogonal transformation is utilized to implement privacy-preserving image retrieval.
Key independent encrypted face clustering
A blind encrypted image classification procedure based on a standard unsupervised clustering algorithm has been used to validate the proposed concept and the feature that remains transparent to this form of encryption is the sorted intensity histogram and its derivatives.
Secure Image Retrieval Based On Orthogonal Decomposition under Cloud Environment
Experimental results prove that the proposed secure image retrieval method based on orthogonal decomposition can achieve better security and better retrieval precision.
Privacy-preserving outsourced image feature extraction
DAP$$^2$$CMH: Deep Adversarial Privacy-Preserving Cross-Modal Hashing
Results show that the proposed approach DAP, named deep adversarial privacy-preserving cross-modal hashing (DAP) outperforms the state-of-the-arts, on three common used benchmarks.
Face anti-spoofing by identity masking using random walk patterns and outlier detection
This work proposes a identity-independent architecture based on random correlated scans of natural face images that tends to capture the pixel correlation statistics with minimal content interference and shows great promise, particularly when trained on natural face sets, using a one-class support vector machine and cross-validated on other databases.
Image similarity based on eigen-correspondences
This eigen-linking process has been found to be robust to several signal processing operations, scaling and noise insertion, despite remaining sufficiently discriminative across perceptually dissimilar images.


Homomorphic encryption-based secure SIFT for privacy-preserving feature extraction
This paper proposes a homomorphic encryption-based secure SIFT method for privacy-preserving feature extraction and representation based on Paillier cryptosystem, and investigates a quantization-like secure comparison strategy for homomorphic comparison.
Authenticating encrypted data
  • S. Kashyap, K. Karthik
  • Computer Science, Mathematics
    2011 National Conference on Communications (NCC)
  • 2011
The main challenge here is to develop a parametric hashing algorithm that is invariant to encryption by allowing a small part of the statistical signature of the original image to emerge despite the encryption process.
Robust and secure image hashing
A novel algorithm for generating an image hash based on Fourier transform features and controlled randomization is developed and it is shown that the proposed hash function is resilient to content-preserving modifications, such as moderate geometric and filtering distortions.
Enabling search over encrypted multimedia databases
Retrieval results on an encrypted color image database and security analysis of the secure indexing schemes under different attack models show that data confidentiality can be preserved while retaining very good retrieval performance.
Secure image retrieval through feature protection
Experimental results show that secure image retrieval can achieve comparable retrieval performance to conventional image retrieval techniques without revealing information about image content.
Random Gray code and its performance analysis for image hashing
A clustering based approach to perceptual image hashing
This paper proposes a polynomial-time heuristic clustering algorithm that automatically determines the final hash length needed to satisfy a specified distortion and proves that the decision version of the clustering problem is NP complete.
Robust image hashing
A novel image indexing technique that may be called an image hash function, which uses randomized signal processing strategies for a non-reversible compression of images into random binary strings, and is shown to be robust against image changes due to compression, geometric distortions, and other attacks.
Perceptual Image Hashing Via Feature Points: Performance Evaluation and Tradeoffs
The proposed image hashing paradigm using visually significant feature points is proposed, which withstands standard benchmark attacks, including compression, geometric distortions of scaling and small-angle rotation, and common signal-processing operations.
Robust image hashing by downsampling: Between mean and median
  • K. Karthik
  • Computer Science, Mathematics
    2011 World Congress on Information and Communication Technologies
  • 2011
Robustness against recompression, noise and most importantly geometric operations, stems from two factors: (a) the random sampling which provides elasticity and (b) the process of selecting the PIN-thresholds as the arithmetic mean filtered set.