Privacy-Preserving Image Captioning with Partial Encryption and Deep Learning

Abstract

Although image captioning has gained remarkable interest, privacy concerns are raised because it relies heavily on images, and there is a risk of exposing sensitive information in the image data. In this study, a privacy-preserving image captioning framework that leverages partial encryption using Double Random Phase Encoding (DRPE) and deep learning is proposed to address privacy concerns. Unlike previous methods that rely on full encryption or masking, our approach involves encrypting sensitive regions of the image while preserving the image’s overall structure and context. Partial encryption ensures that the sensitive regions’ information is preserved instead of lost by masking it with a black or gray box. It also allows the model to process both encrypted and unencrypted regions, which could be problematic for models with fully encrypted images. Our framework follows an encoder–decoder architecture where a dual-stream encoder based on ResNet50 extracts features from the partially encrypted images, and a transformer architecture is employed in the decoder to generate captions from these features. We utilize the Flickr8k dataset and encrypt the sensitive regions using DRPE. The partially encrypted images are then fed to the dual-stream encoder, which processes the real and imaginary parts of the encrypted regions separately for effective feature extraction. Our model is evaluated using standard metrics and compared with models trained on the original images. Our results demonstrate that our method achieves comparable performance to models trained on original and masked images and outperforms models trained on fully encrypted data, thus verifying the feasibility of partial encryption in privacy-preserving image captioning. © 2025 by the authors.