🤖 AI Summary
To address the privacy-accuracy-efficiency trade-off in encrypted-domain deep learning inference for sensitive data sharing, this paper proposes a learnable, key-customized block-wise pixel scrambling encryption method, tightly integrated with Vision Transformers (ViTs). This integration enables, for the first time, end-to-end secure ViT inference over dynamically encrypted inputs. The approach performs high-accuracy, low-overhead model inference directly in the ciphertext domain—without decryption—thereby simultaneously ensuring strong privacy guarantees, computational efficiency, and robustness. Adversarial robust training is further incorporated to enhance security against malicious perturbations. Evaluated on MRI brain tumor and lung/colon cancer pathology datasets, the method achieves 94% classification accuracy and demonstrates strong resilience against diverse adversarial attacks. These results validate its reliability and practicality in real-world, high-sensitivity medical applications.
📝 Abstract
In the era of data-driven decision-making, ensuring the privacy and security of shared data is paramount across various domains. Applying existing deep neural networks (DNNs) to encrypted data is critical and often compromises performance, security, and computational overhead. To address these limitations, this research introduces a secure framework consisting of a learnable encryption method based on the block-pixel operation to encrypt the data and subsequently integrate it with the Vision Transformer (ViT). The proposed framework ensures data privacy and security by creating unique scrambling patterns per key, providing robust performance against adversarial attacks without compromising computational efficiency and data integrity. The framework was tested on sensitive medical datasets to validate its efficacy, proving its ability to handle highly confidential information securely. The suggested framework was validated with a 94% success rate after extensive testing on real-world datasets, such as MRI brain tumors and histological scans of lung and colon cancers. Additionally, the framework was tested under diverse adversarial attempts against secure data sharing with optimum performance and demonstrated its effectiveness in various threat scenarios. These comprehensive analyses underscore its robustness, making it a trustworthy solution for secure data sharing in critical applications.