A Privacy Protection Framework for Medical Image Security without Key Dependency Based on Visual Cryptography and Trusted Computing

Abstract

The development of mobile Internet and the popularization of intelligent sensor devices greatly facilitate the generation and transmission of massive multimedia data including medical images and pathological models on the open network. The popularity of artificial intelligence (AI) technologies has greatly improved the efficiency of medical image recognition and diagnosis. However, it also poses new challenges to the security and privacy of medical data. The leakage of medical images related to users’ privacy is emerging one after another. The existing privacy protection methods based on cryptography or watermarking often bring a burden to image transmission. In this paper, we propose a privacy-preserving recognition network for medical images (called MPVCNet) to solve these problems. MPVCNet uses visual cryptography (VC) to transmit images by sharing. Benefiting from the secret-sharing characteristics of VC, MPVCNet can securely transmit images in clear text, which can both protect privacy and mitigate performance loss. Aiming at the problem that VC is easy to forge, we combine trusted computing environments (TEE) and blind watermarking technologies to embed verification information into sharing images. We further leverage the transfer learning technology to abate the side effect resulting from the use of visual cryptography. The results of the experiment show that our approach can maintain the trustworthiness and recognition performance of the recognition networks while protecting the privacy of medical images.

Enhanced Semantic Visual Cryptography with AI-driven error reduction for improved two-dimensional image quality and security

“…For an image with dimensions M × N, the complexity of the algorithm is O (MN), as each pixel is processed once per iteration. However, the total complexity may increase depending on the number of iterations required for the RL to converge to an optimal policy [27] Policy Optimization (PPO) or Deep Deterministic Policy Gradients (DDPG) can enhance learning efficiency, but at the cost of increased computational overhead [24].…”

“…(b) Filtering Attacks: These involve applying filters to degrade image quality. The EER's use of RL allows the system to learn from various instances of filtered images, enabling it to reverse-engineer the effects and restore the image to its original state [27]. (c) Compression Attacks: Compression can introduce artifacts that degrade image integrity.…”

“…(c) Compression Attacks: Compression can introduce artifacts that degrade image integrity. The RLPA component of the EER algorithm can adapt to these artifacts, optimizing the image restoration process to ensure that semantic meaning is not lost after decompression [27]. (d) Geometric Attacks: Such attacks distort the image through rotation, scaling, or other geometric transformations.…”