Achieving a balance between security and retrieval accuracy presents a significant challenge in secure content-based image retrieval (SCBIR), particularly in untrusted cloud environments. Conventional SCBIR schemes often struggle with trade-offs, either compromising data privacy, reducing retrieval performance, or introducing significant computational overhead, making them unsuitable for large-scale real-world applications. To overcome these challenges, we propose SCBIR-PE, a novel SCBIR scheme that integrates block-based perceptual encryption with an efficient histogram-based feature extraction method. The encryption incorporates geometric and color transformations at block and sub-block levels across three distinct extensions, confirming security robustness while preserving image features necessary for an image retrieval application. Thus, feature extraction is performed using the Color and Edge Directivity Descriptor (CEDD), enabling direct feature computation in the encrypted domain. Additionally, Euclidean distance is utilized as a similarity measurement technique, ensuring efficient image retrieval while avoiding computationally intensive tasks like clustering, index generation, or feature mapping, which are at the core of existing SCBIR schemes. Experimental evaluations demonstrate that SCBIR-PE scheme outperforms conventional privacy preserving image retrieval schemes in terms of retrieval accuracy (up to 4% better mean average precision score), security robustness, and computational efficiency. By ensuring strong privacy protection with minimal computational overhead, our proposed scheme offers a scalable and efficient solution for cloud-assisted secure image retrieval applications.

Cloud-edge collaboration provides an efficient way to promote the development and application of the Artificial Intelligence of Things (AIoT) by addressing the limited computing, communication, and storage capabilities of the Internet of Things (IoT) devices. The compute-intensive task of developing an Artificial Intelligence (AI) model is performed on the cloud-server over a public dataset while it is deployed on the edge-server to analyze the IoT data. The merit in processing data locally is the privacy preservation. However, to keep the model relevant to the ever-growing IoT data, it is necessary to share it with the cloud-server, which can raise certain privacy concerns. Also, it is challenging to adapt the model to the IoT data characteristics. Therefore, we propose a privacy-preserving cloud-edge paradigm incorporating personalized context learning and incremental learning strategies to adapt the trained model to the heterogeneous and dynamic IoT environment. To avoid any privacy issues, we propose a lightweight image cryptosystem parameterized to protect image contents according to an application requirement. The simulation results show that our proposed image cryptosystem has favorable encryption properties and the cipher-images are learnable by an AI model. In addition, our incremental learning strategy efficiently kept the model up-to-date, and with proposed personalized context learning strategy, the cloud-server model’s performance improved up to 13% for plain-images and 18% for cipher-images.

Channel correction plays an important role in performance of wireless communication systems. In conventional systems, channel estimation is one of the blocks at receiver side to compute channel impulse response. Various algorithms have been proposed to make them efficient and improve their performance. However, precise channel estimation incurs additional computational cost and increases complexity of the overall system. In this study, we have considered the otherwise to bypass channel estimation of an Orthogonal Frequency Division Multiplexing (OFDM) based image communication system designed to enable cloud-based deep learning (DL) computation. The simulations present performance analysis of OFDM system with and without channel correction in-terms of bit error rate (BER), and two image quality measures. Recovered image quality difference between the two systems significantly increases with higher Eb/N0. For inferencing analysis, in higher Eb/N0regions, model performance on images recovered with correction is same as on the original images while lags behind by 6% on images without correction. In lower Eb/N0regions, the model accuracy reduces by 10% on average for both systems. In addition, the model accuracy shows overlapping pattern in that region and for 3 dB, it has performed better on images recovered without correction.