Secure transmission of medical images and medical data is essential in healthcare systems, both in telemedicine and AI approaches. The compromise of images and medical data could affect patient privacy and the accuracy of diagnosis. Digital watermarking embeds medical images into a non-significant image before transmission to ensure visual security. However, it is vulnerable to white-box attacks because the embedded medical image can be extracted by an attacker that knows the system’s operation and does not ensure the authenticity of image transmission. A visually secure image encryption scheme for secure fingerprint-based authenticated transmission has been proposed to solve the above issues. The proposed scheme embeds the encrypted medical image, the encrypted physician’s fingerprint, and the patient health record (EHR) into a non-significant image to ensure integrity, authenticity, and confidentiality during the medical image and medical data transmission. A chaotic encryption algorithm based on a permutation key has been used to encrypt the medical image and fingerprint feature vector. A hybrid asymmetric cryptography scheme based on Elliptic Curve Cryptography (ECC) and AES has been implemented to protect the permutation key. Simulations and comparative analysis show that the proposed scheme achieves higher visual security of the encrypted image and higher medical image reconstruction quality than other secure image encryption approaches.

Federated Learning (FL) is a decentralized and collaborative learning approach that ensures the data privacy of each participant. However, recent studies have shown that the private data of each participant can be obtained from shared parameters of local models through reversal model and membership inference attacks leading to privacy leakage. Privacy-preserving federated learning strategies based on Homomorphic Encryption (PPFL-HE) have been developed to solve this issue. PPFL-HE methods require high communication and computational overheads, which are impractical for resource-limited devices. This work proposes an efficient PPFL-HE method to reduce communication and computational overheads. The proposed method is based on an innovative quantization process that introduces a dynamic range evaluation layer-for-layer (DREL) to encode the weights of the local models into long-signed integers. Compared to standard quantization approaches, the proposed method reduces the quantization errors and the communication overhead. Moreover, it enables the encryption of local weights with the Brakerski/Fan-Vercauteren Homomorphic Encryption scheme (BFV-HE), which is highly efficient on integers, reducing encryption, aggregation, decryption time, and ciphertext size. The experiments conducted with five popular datasets and four different Machine Learning (ML) models (three CNN models and a feedforward neural network) show that the proposed method is more efficient in communication and computational overheads than other PPFL-HE methods. Specifically, the proposed method requires fewer FL rounds to achieve global model convergence and leads to an average reduction in encryption time of 99.95% and 73.79%, in decryption time of 99.90% and 55.13%, and in ciphertext size of 5.78% and 75.17% compared to PPFL-HE methods based on Paillier and CKKS schemes, respectively.

Human activity recognition (HAR) through gait analysis is a very promising research area for early detection of neurodegenerative diseases because gait abnormalities are typical symptoms of some neurodegenerative diseases, such as early dementia. While working with such biometric data, the performance parameters must be considered along with privacy and security issues. In other words, such biometric data should be processed under specific security and privacy requirements. This work proposes an innovative hybrid protection scheme combining a partially homomorphic encryption scheme and a cancelable biometric technique based on random projection to protect gait features, ensuring patient privacy according to ISO/IEC 24745. The proposed hybrid protection scheme has been implemented along a long short-term memory (LSTM) neural network to realize a secure early dementia diagnosis system. The proposed protection scheme is scalable and implementable with any type of neural network because it is independent of the network’s architecture. The conducted experiments demonstrate that the proposed protection scheme enables a high trade-off between safety and performance. The accuracy degradation is at most 1.20% compared with the early dementia recognition system without the protection scheme. Moreover, security and computational analyses of the proposed scheme have been conducted and reported.

The rapid advancement of Deep Learning (DL) techniques has led to the widespread proliferation of DeepFake (DF) images, raising real-world concerns. In this work, DeepDect is proposed and evaluated in a real-world scenario. The platform has been developed using a human-centered approach, integrating insights (requirements) from both common and DF expert users. The platform can detect both face-swapping and generated deepfake faces, which are the most common cases of DF in the current context. Two benchmarks have been conducted to evaluate state-of-the-art DF detection models for face-swap and AI-generated images. The best-performing models (ResNet-50 and Random Forest for face-swapping detection, Capsule Forensics v2, and CNN for AI-generated images) have been integrated into the platform as the detection engine. An Explainable AI (XAI) module has been implemented and integrated into DeepDect to provide visual (Grad-CAM heatmaps) and textual explanations, enhancing interpretability and user trust. A real-world evaluation involving 108 participants was performed to assess DeepDect’s effectiveness compared to human detection. DeepDect has achieved 81% detection accuracy, outperforming human users, underscoring the need for such a tool in real-world applications. These findings have highlighted the importance of accessible, explainable, and high-performing AI solutions, offering a balance between technical robustness and User-Centric Design (UCD).