# A Privacy-Protected Image Retrieval Scheme for Fast and Secure Image Search

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Related Works

#### 2.1. Privacy Protection Image Retrieval Scheme

#### 2.2. Explanation of Key Technologies in the Scheme

#### 2.2.1. 4-D Hyperchaotic System

#### 2.2.2. Advanced Encryption Standard

#### 2.2.3. Privacy Protection and Retrieval

## 3. The Proposed Method

#### 3.1. Privacy Protection Scheme

#### 3.2. Image Encryption

_{1}, B

_{2},..., B

_{k}, where k is the number of blocks. (2) Generate a random matrix of the same size as a normal image by logistic chaotic mapping. The random matrix is expressed as R. (3) A random chaotic sequence is generated by a 4-D hyperchaotic system. According to Formula 1, the four hyperchaotic sequences are y

_{1}, y

_{2}, y

_{3}, y

_{4}. (4) Select a DNA encoding and decoding method for each sub-block of the plain image and random matrix based on sequence y

_{3}. (5) Select the DNA calculation method between the two sub-blocks based on sequence y

_{1}and sequence y

_{2}. (6) Combine all the encrypted sub-blocks together to form an encrypted image based on sequence y

_{4}. The process of image encryption and decryption is reversed.

#### 3.3. Index Encryption

## 4. Experimental Evaluation

#### 4.1. Search Scheme Comparison

#### 4.2. Encryption Performance Analysis

#### 4.2.1. Sensitivity Analysis

#### 4.2.2. Histogram Analysis

#### 4.2.3. Correlation Analysis

#### 4.2.4. Blocking Attack Analysis

#### 4.2.5. Differential Attack Analysis

#### 4.2.6. Statistical Analysis

#### 4.3. Retrieval Performance Comparison

## 5. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Cheng, B.; Zhuo, L.; Bai, Y. Secure Index Construction for Privacy-Preserving Large-Scale Image Retrieval. In Proceedings of the 2014 IEEE Fourth International Conference on Big Data and Cloud Computing, Sydney, NSW, Australia, 4 December 2014; pp. 116–120. [Google Scholar]
- Ferreira, B.; Rodrigues, J.; Leitao, J.; Domingos, H. Practical Privacy-Preserving Content-Based Retrieval in Cloud Image Repositories. IEEE Trans. Cloud Comput.
**2019**, 7, 784–798. [Google Scholar] [CrossRef] - Xia, Z.; Xiong, N.N.; Vasilakos, A.V.; Sun, X. EPCBIR: An efficient and privacy-preserving content-based image retrieval scheme in cloud computing. Inf. Sci.
**2017**, 387, 195–204. [Google Scholar] [CrossRef] - Zhu, X.; Li, H.; Guo, Z. Privacy-preserving query over the encrypted image in cloud computing. J. XiDian Univ.
**2014**, 41, 151–158. [Google Scholar] - Ibrahim, A.; Jin, H.; Yassin, A.A.; Zou, D.; Xu, P. Towards Efficient Yet Privacy-Preserving Approximate Search in Cloud Computing. Comput. J.
**2014**, 57, 241–254. [Google Scholar] [CrossRef] - Fan, K.; Wang, X.; Suto, K.; Li, H.; Yang, Y. Secure and Efficient Privacy-Preserving Ciphertext Retrieval in Connected Vehicular Cloud Computing. IEEE Netw.
**2018**, 32, 52–57. [Google Scholar] [CrossRef] - Xia, Z.; Wang, X.; Zhang, L.; Qin, Z.; Sun, X.; Ren, K. A Privacy-Preserving and Copy-Deterrence Content-Based Image Retrieval Scheme in Cloud Computing. IEEE Trans. Inf. Forensics Secur.
**2016**, 11, 2594–2608. [Google Scholar] [CrossRef] - Feng, W.; He, Y. Cryptanalysis and Improvement of the Hyper-Chaotic Image Encryption Scheme Based on DNA Encoding and Scrambling. IEEE Photon. J.
**2018**, 10, 1–15. [Google Scholar] [CrossRef] - Zhu, Z.-L.; Zhang, W.; Wong, K.-W.; Yu, H. A chaos-based symmetric image encryption scheme using a bit-level permutation. Inf. Sci.
**2011**, 181, 1171–1186. [Google Scholar] [CrossRef] - Ravichandran, D.; Praveenkumar, P.; Rayappan, J.B.B.; Amirtharajan, R. Chaos based crossover and mutation for securing DICOM image. Comput. Boil. Med.
**2016**, 72, 170–184. [Google Scholar] [CrossRef] - Chen, J.-X.; Zhu, Z.-L.; Fu, C.; Yu, H.; Zhang, L.-B. A fast chaos-based image encryption scheme with a dynamic state variables selection mechanism. Commun. Nonlinear Sci. Numer. Simul.
**2015**, 20, 846–860. [Google Scholar] [CrossRef] - Chai, X.; Chen, Y.; Broyde, L. A novel chaos-based image encryption algorithm using DNA sequence operations. Opt. Lasers Eng.
**2017**, 88, 197–213. [Google Scholar] [CrossRef] - Xu, L.; Li, Z.; Li, J.; Hua, W. A novel bit-level image encryption algorithm based on chaotic maps. Opt. Lasers Eng.
**2016**, 78, 17–25. [Google Scholar] [CrossRef] - Wang, J.; Long, F. CNN-based color image encryption algorithm using DNA sequence operations. In Proceedings of the 2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC), Shenzhen, China, 15–17 December 2017; pp. 730–736. [Google Scholar]
- Enayatifar, R.; Abdullah, A.H.; Isnin, I.F.; Altameem, A.; Lee, M. Image encryption using a synchronous permutation-diffusion technique. Opt. Lasers Eng.
**2017**, 90, 146–154. [Google Scholar] [CrossRef] - Liu, W.; Sun, K.; Zhu, C. A fast image encryption algorithm based on chaotic map. Opt. Lasers Eng.
**2016**, 84, 26–36. [Google Scholar] [CrossRef] - Datar, M.; Immorlica, N.; Indyk, P.; Mirrokni, V.S. Locality-sensitive hashing scheme based on p-stable distributions. In Proceedings of the 20th Annual Symposium on Computational Geometry, Brooklyn, NY, USA, 9–11 June 2004; pp. 253–262. [Google Scholar]
- Xia, P.; Pan, Y.; Lai, H.; Liu, C.; Yan, S. Supervised hashing for image retrieval via image representation learning. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence(AAAI), Québec City, QC, USA, 27–31 July 2014; pp. 2156–2162. [Google Scholar]
- Shen, F.; Shen, C.; Liu, W.; Shen, H.T. Supervised Discrete Hashing. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015; pp. 37–45. [Google Scholar]
- Li, W.-J.; Wang, S.; Kang, W.-C. Feature Learning Based Deep Supervised Hashing with Pairwise Labels; IJCAI: New York, NY, USA, 2016; pp. 3270–3278. [Google Scholar]
- Li, Q.; Sun, Z.; He, R.; Tan, T. Deep supervised discrete hashing. In Advances in Neural Information Processing Systems; NIPS: Long Beach, CA, USA, 2017; pp. 2482–2491. [Google Scholar]
- Li, N.; Li, C.; Deng, C.; Liu, X.; Gao, G. Deep joint semantic-embedding hashing. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18), Stockholm, Sweden, 13–19 July 2018; pp. 2397–2403. [Google Scholar]
- Jiang, Q.; Cui, X.; Li, W. Deep Discrete Supervised Hashing. IEEE Trans. Image Process.
**2018**, 27, 5996–6009. [Google Scholar] [CrossRef] [PubMed] - Nazarimehr, F.; Rajagopal, K.; Kengne, J.; Jafari, S.; Pham, V.T. A new four-dimensional system containing chaotic or hyper-chaotic attractors with no equilibrium, a line of equilibria and unstable equilibria. Chaos Solitons Fractals
**2018**, 111, 108–118. [Google Scholar] [CrossRef] - Zhang, Y.; Zhang, Q.; Liao, H.; Wu, W.; Li, X.; Niu, H. A Fast Image Encryption Scheme Based on Public Image and Chaos. In Proceedings of the 2017 International Conference on Computing Intelligence and Information System (CIIS), Nanjing, China, 21–23 April 2017; pp. 270–276. [Google Scholar]
- Deshmukh, P.; Kolhe, V. Modified AES based algorithm for MPEG video encryption. In Proceedings of the International Conference on Information Communication and Embedded Systems (ICICES2014), Chennai, India, 27–28 February 2014; pp. 1–5. [Google Scholar]
- Cisse, I.I.; Kim, H.; Ha, T. A rule of seven in Watson-Crick base-pairing of mismatched sequences. Nat. Struct. Mol. Biol.
**2012**, 19, 623–627. [Google Scholar] [CrossRef] - Zhang, X.Q.; Wang, X.S. Multiple-image encryption algorithm based on DNA encoding and chaotic system. Multimed. Tools Appl.
**2018**, 77, 1–29. [Google Scholar] [CrossRef] - Wang, X.Y.; Zhang, Y.Q.; Bao, X.M. A novel chaotic image encryption scheme using DNA sequence operations. Opt. Lasers Eng.
**2015**, 73, 53–61. [Google Scholar] [CrossRef] - Murat, H.; Zhang, S.; Yan, C. Classification of Xinjiang Uygur medicine image based on KNN Classifier. J. Xinjiang Med. Univ.
**2015**, 38, 800–804. [Google Scholar] - Rong, H.; Wang, H.; Liu, J.; Wu, W.; Xian, M. Efficient Integrity Verification of Secure Outsourced kNN Computation in Cloud Environments. In Proceedings of the 2016 IEEE Trustcom/BigDataSE/ISPA, Tianjin, China, 23–26 August 2016; pp. 236–243. [Google Scholar]
- Wong, W.K.; Cheung, D.W.-L.; Kao, B.; Mamoulis, N. Secure kNN computation on encrypted databases. In Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2009, Providence, RI, USA, June 29–July 2 2009. [Google Scholar]
- Choi, S.; Ghinita, G.; Lim, H.; Bertino, E. Secure kNN Query Processing in Untrusted Cloud Environments. IEEE Trans. Knowl. Data Eng.
**2014**, 26, 2818–2831. [Google Scholar] [CrossRef]

**Figure 4.**Key sensitivity analysis. (

**a**) Encrypted image. (

**b**) Fine-tuning the private key 1. (

**c**) Fine-tuning the private key 2. (

**d**) Fine-tuning the private key 3. (

**e**) Fine-tuning the private key 4. (

**f**) Fine-tuning the private key 5. (

**g**) Fine-tuning the private key 6. (

**h**) Original private key decryption.

**Figure 5.**Histogram analysis. (

**a**) Plaintext. (

**b**) Ciphertext. (

**c**) Plaintext R-channel histogram. (

**d**) Ciphertext R-channel histogram. (

**e**) Plaintext G-channel histogram. (

**f**) Ciphertext G-channel histogram. (

**g**) Plaintext B-channel histogram. (

**h**) Ciphertext B-channel histogram.

**Figure 6.**Correlation of images. (

**a**) R channel in original image. (

**b**) R channel in encrypted image. (

**c**) G channel in original image. (

**d**) G channel in encrypted image. (

**e**) B channel in original image. (

**f**) B channel in encrypted image.

**Figure 7.**Blocking attack. (

**a**) Encrypted image. (

**b**) Decrypted image. (

**c**) A 1/4 degree blocking of the encrypted image. (

**d**) A 1/4 degree blocking of the decrypted image. (

**e**) A 1/2 degree blocking of the decrypted image. (

**f**) A 1/2 degree blocking of the encrypted image. (

**g**) Blocking encrypted image by 3/4. (

**h**) A 3/4 degree blocking of the decrypted image.

**Figure 11.**The precision recall curve of the algorithms. (

**a**) the precision recall curve for AlexNet and ResNet18 with different bits. (

**b**) the precision recall curve of the proposed algorithm and ResNet50 under different bits.

**Table 1.**The performance of the number of pixels change rate (NPCR) and unified average changing intensity (UACI).

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Du, A.; Wang, L.; Cheng, S.; Ao, N.
A Privacy-Protected Image Retrieval Scheme for Fast and Secure Image Search. *Symmetry* **2020**, *12*, 282.
https://doi.org/10.3390/sym12020282

**AMA Style**

Du A, Wang L, Cheng S, Ao N.
A Privacy-Protected Image Retrieval Scheme for Fast and Secure Image Search. *Symmetry*. 2020; 12(2):282.
https://doi.org/10.3390/sym12020282

**Chicago/Turabian Style**

Du, Anyu, Liejun Wang, Shuli Cheng, and Naixiang Ao.
2020. "A Privacy-Protected Image Retrieval Scheme for Fast and Secure Image Search" *Symmetry* 12, no. 2: 282.
https://doi.org/10.3390/sym12020282