Chaotic Encryption Algorithm with Key Controlled Neural Networks for Intelligent Transportation Systems
The security of sensitive information is vital in many aspects of multimedia applications. In particular, security in Intelligent Transportation Systems involving traffic data collection, analysis and manipulations is essential. Images captured by roadside units that form the basis of many traffic rerouting and manipulation techniques should take all precautions necessary to deter unwanted traffic behaviour caused by malicious adversaries. We present a new image encryption algorithm using chaotic key controlled neural networks for use in roadside units. The encryption algorithm is based on the Lorenz chaotic system and the novel key controlled finite field neural network. The encryption scheme is found to have substantial cryptographic strength with up to 5% increase in information entropy, suitable mixing properties, and consistent resistance to common attacks (less than 0.002 % difference in NPCR and 0.3% UACI metrics for different test images).