Cited By
View all- Zhao RZhang YWang TWen WXiang YCao X(2024)Visual Content Privacy Protection: A SurveyACM Computing Surveys10.1145/3708501Online publication date: 16-Dec-2024
The Illusion of Visual Security: Reconstructing Perceptually Encrypted Images
Pages 3998 - 4010
Abstract
Perceptual image encryption degrades image quality by selectively encrypting some key information of the plain images. The encrypted images are partially perceptible according to the security or quality requirements. Although several types of attacks have tried to infer privacy information from the encrypted images, they can only either extract statistical information or enhance image sketch. In this paper, we take one step further and fully recover the plain images from perceptually encrypted counterparts by designing a non-local attack network (NL-ANet). NL-ANet is composed of densely cascaded multiscale non-local modules (MSNL) and a hierarchical attention fusion module (HAFM). In particular, to better reconstruct encryption distortion, we introduce MSNL to capture powerful hierarchical features from different scales, and propose HAFM to adaptively aggregate and enhance informative hierarchical features for reconstruction. We also propose a new instantiation of the multi-head non-local block with channel attention (MHCA) to explore the long-range dependencies of global contextual information. Extensive experiments show that NL-ANet is encryption-agnostic and superior on different perceptual encryption schemes under different encryption strengths. NL-ANet also achieves better performance than state-of-the-art image restoration methods.
References
[1]
P. Zheng and J. Huang, “An efficient image homomorphic encryption scheme with small ciphertext expansion,” in Proc. 21st ACM Int. Conf. Multimedia, Oct. 2013, pp. 803–812.
[2]
G. Ye and X. Huang, “An image encryption algorithm based on autoblocking and electrocardiography,” IEEE MultiMedia, vol. 23, no. 2, pp. 64–71, Apr./Jun. 2016.
[3]
G. Ye, “Image scrambling encryption algorithm of pixel bit based on chaos map,” Pattern Recognit. Lett., vol. 31, no. 5, pp. 347–354, Apr. 2010.
[4]
X. Mao, C. Shen, and Y.-B. Yang, “Image restoration using very deep convolutional encoder–decoder networks with symmetric skip connections,” in Proc. Adv. Neural Inf. Process. Syst., vol. 29, 2016, pp. 1–9.
[5]
Y. Gou, B. Li, Z. Liu, S. Yang, and X. Peng, “CLEARER: Multi-scale neural architecture search for image restoration,” in Proc. Adv. Neural Inf. Process. Syst., vol. 33, 2020, pp. 17129–17140.
[6]
D. Liu, B. Wen, Y. Fan, C. C. Loy, and T. S. Huang, “Non-local recurrent network for image restoration,” in Proc. Adv. Neural Inf. Process. Syst., vol. 31, 2018, pp. 1–10.
[7]
J. Dong, S. Roth, and B. Schiele, “Deep Wiener deconvolution: Wiener meets deep learning for image deblurring,” in Proc. NIPS, vol. 33, 2020, pp. 1048–1059.
[8]
S. Wanet al., “Deep convolutional-neural-network-based channel attention for single image dynamic scene blind deblurring,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 8, pp. 2994–3009, Aug. 2021.
[9]
G. Taoet al., “Spectrum-to-kernel translation for accurate blind image super-resolution,” in Proc. Adv. Neural Inf. Process. Syst., vol. 34, 2021, pp. 22643–22654.
[10]
H. Chen, X. He, H. Yang, L. Qing, and Q. Teng, “A feature-enriched deep convolutional neural network for JPEG image compression artifacts reduction and its applications,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 1, pp. 430–444, Jan. 2022.
[11]
B. Zheng, Y. Chen, X. Tian, F. Zhou, and X. Liu, “Implicit dual-domain convolutional network for robust color image compression artifact reduction,” IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 11, pp. 3982–3994, Nov. 2020.
[12]
Z. Jin, M. Z. Iqbal, W. Zou, X. Li, and E. Steinbach, “Dual-stream multi-path recursive residual network for JPEG image compression artifacts reduction,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 2, pp. 467–479, Feb. 2021.
[13]
A. Lahiri, S. Bairagya, S. Bera, S. Haldar, and P. K. Biswas, “Lightweight modules for efficient deep learning based image restoration,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 4, pp. 1395–1410, Apr. 2021.
[14]
C. Liu, F. Wu, and X. Wang, “EFINet: Restoration for low-light images via enhancement-fusion iterative network,” IEEE Trans. Circuits Syst. Video Technol., vol. 32, no. 12, pp. 8486–8499, Dec. 2022.
[15]
Y. Hu, J. Li, Y. Huang, and X. Gao, “Image super-resolution with self-similarity prior guided network and sample-discriminating learning,” IEEE Trans. Circuits Syst. Video Technol., vol. 32, no. 4, pp. 1966–1985, Apr. 2022.
[16]
Y. Zhou, K. Panetta, and S. Aagaian, “Partial multimedia encryption with different security levels,” in Proc. IEEE Conf. Technol. Homeland Secur., May 2008, pp. 513–518.
[17]
P. Jagadeesh, P. Nagabhushan, and R. Pradeep Kumar, “A novel perceptual image encryption scheme using geometric objects based kernel,” Int. J. Comput. Sci. Inf. Technol., vol. 5, no. 4, pp. 165–173, Aug. 2013.
[18]
I. Ahmad and S. Shin, “A pixel-based encryption method for privacy-preserving deep learning models,” 2022, arXiv:2203.16780.
[19]
W. Sirichotedumrong, Y. Kinoshita, and H. Kiya, “Pixel-based image encryption without key management for privacy-preserving deep neural networks,” IEEE Access, vol. 7, pp. 177844–177855, 2019.
[20]
G. Bhatnagar and Q. M. Jonathan Wu, “Selective image encryption based on pixels of interest and singular value decomposition,” Digit. Signal Process., vol. 22, no. 4, pp. 648–663, Jul. 2012.
[21]
F. J. Dyson and H. Falk, “Period of a discrete cat mapping,” Amer. Math. Monthly, vol. 99, no. 7, pp. 603–614, Aug. 1992.
[22]
K. Kurihara, S. Imaizumi, S. Shiota, and H. Kiya, “An encryption-then-compression system for lossless image compression standards,” IEICE Trans. Inf. Syst., vol. 100, no. 1, pp. 52–56, 2017.
[23]
M. Preishuber, T. Hütter, S. Katzenbeisser, and A. Uhl, “Depreciating motivation and empirical security analysis of chaos-based image and video encryption,” IEEE Trans. Inf. Forensics Security, vol. 13, no. 9, pp. 2137–2150, Sep. 2018.
[24]
B. Hou, Y. Li, H. Zhao, and B. Wu, “Linear attack on round-reduced des using deep learning,” in Proc. Eur. Symp. Res. Comput. Secur., 2020, pp. 131–145.
[25]
W.-S. Yap, R. C.-W. Phan, W.-C. Yau, and S.-H. Heng, “Cryptanalysis of a new image alternate encryption algorithm based on chaotic map,” Nonlinear Dyn., vol. 80, no. 3, pp. 1483–1491, May 2015.
[26]
J. Kim, J. K. Lee, and K. M. Lee, “Accurate image super-resolution using very deep convolutional networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 1646–1654.
[27]
W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang, “Deep Laplacian pyramid networks for fast and accurate super-resolution,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 5835–5843.
[28]
Y. Tai, J. Yang, X. Liu, and C. Xu, “MemNet: A persistent memory network for image restoration,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 4539–4547.
[29]
Y. Zhang, Y. Tian, Y. Kong, B. Zhong, and Y. Fu, “Residual dense network for image restoration,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 7, pp. 2480–2495, Jul. 2021.
[30]
Y. Hang, Q. Liao, W. Yang, Y. Chen, and J. Zhou, “Attention cube network for image restoration,” in Proc. 28th ACM Int. Conf. Multimedia, Oct. 2020, pp. 2562–2570.
[31]
T. Xiang, Y. Yang, S. Guo, H. Liu, and H. Liu, “PRNet: A progressive recovery network for revealing perceptually encrypted images,” in Proc. 29th ACM Int. Conf. Multimedia, Oct. 2021, pp. 3537–3545.
[32]
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 936–944.
[33]
A. L. Maas, A. Y. Hannun, and A. Y. Ng, “Rectifier nonlinearities improve neural network acoustic models,” in Proc. Int. Conf. Mach. Learn., 2013, vol. 30, no. 1, p. 3.
[34]
X. Wang, R. Girshick, A. Gupta, and K. He, “Non-local neural networks,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 7794–7803.
[35]
A. Vaswaniet al., “Attention is all you need,” in Proc. Adv. Neural Inf. Process. Syst., vol. 30, 2017, pp. 1–11.
[36]
Y. Yang, T. Xiang, H. Liu, and X. Liao, “Convolutional neural network for visual security evaluation,” IEEE Trans. Circuits Syst. Video Technol., vol. 31, no. 8, pp. 3293–3307, Aug. 2021.
[37]
P. Arbeláez, M. Maire, C. Fowlkes, and J. Malik, “Contour detection and hierarchical image segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 5, pp. 898–916, May 2011.
[38]
M. Bevilacqua, A. Roumy, C. Guillemot, and M.-L.-A. Morel, “Low-complexity single-image super-resolution based on nonnegative neighbor embedding,” in Proc. Brit. Mach. Vis. Conf., 2012, p. 135.
[39]
K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,” IEEE Trans. Image Process., vol. 26, no. 7, pp. 3142–3155, Jul. 2017.
[40]
H. Sheikh. (2005). LIVE Image Quality Assessment Database Release 2. [Online]. Available: https://live.ece.utexas.edu/research/quality
[41]
Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong, and Y. Fu, “Image super-resolution using very deep residual channel attention networks,” in Proc. Eur. Conf. Comput. Vis., 2018, pp. 286–301.
[42]
Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Trans. Image Process., vol. 13, no. 4, pp. 600–612, Apr. 2004.
[43]
L. Tong, F. Dai, Y. Zhang, and J. Li, “Visual security evaluation for video encryption,” in Proc. 18th ACM Int. Conf. Multimedia, Oct. 2010, pp. 835–838.
[44]
T. Xiang, Y. Yang, H. Liu, and S. Guo, “Visual security evaluation of perceptually encrypted images based on image importance,” IEEE Trans. Circuits Syst. Video Technol., vol. 30, no. 11, pp. 4129–4142, Nov. 2020.
Recommendations
Visual Security Index Combining CNN and Filter for Perceptually Encrypted Light Field Images
Visual security index (VSI) represents a quantitative index for the visual security evaluation of perceptually encrypted images. Recently, the research on visual security of encrypted light field (LF) images faces two challenges. One is that the existing ...
On Security Notions for Verifiably Encrypted Signature
IAS '09: Proceedings of the 2009 Fifth International Conference on Information Assurance and Security - Volume 02First we revisit three (BGLS, MBGLS and GZZ) verifiably encrypted signature schemes \cite{BGLS03,H04,GZZ05}. We find that they are all not strong unforgeable. We remark that the notion of existential unforgeable is not sufficient for fair exchange ...
Security of Verifiably Encrypted Signatures and a Construction without Random Oracles
Pairing '09: Proceedings of the 3rd International Conference Palo Alto on Pairing-Based CryptographyIn a verifiably encrypted signature scheme, signers encrypt their signature under the public key of a trusted third party and prove that they did so correctly. The security properties, due to Boneh et al. (Eurocrypt 2003), are unforgeability and ...
Comments
Information & Contributors
Information
Published In
1051-8215 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Press
Publication History
Published: 19 October 2023
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 13 Jan 2025
Other Metrics
Citations
Cited By
View all- Zhao RZhang YWang TWen WXiang YCao X(2024)Visual Content Privacy Protection: A SurveyACM Computing Surveys10.1145/3708501Online publication date: 16-Dec-2024