A Novel Chaos-based Light-weight Image Encryption Scheme for Multi-modal Hearing Aids

Multimodal hearing aids (HAs) aim to deliver more intelligible audio in noisy environments by contextually sensing and processing data in the form of not only audio but also visual information (e.g. lip reading). Machine learning techniques can play a pivotal role for the contextual processing of multimodal data, however, due to the low computational power of the HA devices, the data must be processed either on the edge or cloud which, in turn, poses privacy concerns for the users' sensitive data. Existing literature proposes several techniques for data encryption but their computational complexity is a major bottleneck to meet strict latency requirements for the development of future multi-modal hearing aids. To overcome this problem, this paper proposes a novel real-time audio/visual data encryption scheme based on chaos-based encryption using the Tangent-Delay Ellipse Reflecting Cavity-Map System (TD-ERCS) and Non-linear Chaotic (NCA) Algorithms. The results achieved against different security analysis parameters such as Correlation Coefficient, Unified Averaged Changed Intensity (UACI), Key Sensitivity Analysis, Number of Changing Pixel Rate (NPCR), Mean-Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Entropy test, and Chi-test, indicate that the proposed scheme is more secure with increased key-space against modern brute-force attacks and lightweight as compared to existing schemes.