A neural network approach for visual cryptography

Visual cryptography finds many applications in the cryptographic field such as key management, message concealment, authorization, authentication, identification, and entertainment. The authors propose a novel approach for visual cryptography using neural networks (NNs). To perform encrypting, the input to the NN is a set of gray level images, and the output is a set of binary images (shares) that fulfils the desirable access scheme. This approach is considerably different from the traditional one, and can be applied to cope with very complex access schemes.

[1]  Alfredo De Santis,et al.  Visual Cryptography for General Access Structures , 1996, Inf. Comput..

[2]  Li-Chen Fu,et al.  A local-minima-free neural network approach to building A/D converters and associative adders , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[3]  Tai-Wen Yue,et al.  An auto-invertible neural network for image halftoning and restoration , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[4]  Moni Naor,et al.  Visual Authentication and Identification , 1997, CRYPTO.

[5]  Li-Chen Fu,et al.  A complete neural network approach to solving a class of combinatorial problems , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[6]  Moni Naor,et al.  Visual Cryptography , 1994, Encyclopedia of Multimedia.

[7]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.