"Implications of Neural Compression to Scientific Images" by João Phillipe Cardenuto, Joshua Krinsky et al.
 

Document Type

Conference Proceeding

Publication Date

6-17-2025

Publication Title

IH&MMSEC '25: Proceedings of the ACM Workshop on Information Hiding and Multimedia Security

Pages

80-85

Publisher Name

Association for Computing Machinery

Abstract

While neural compression has the potential to revolutionize image compression, recent studies have emphasized its ability to introduce subtle artifacts that could alter the image content. Concerned about the impact of such modifications on scientific images, this work explores the potential effects of neural compression on these images, focusing on two critical aspects: semantic understanding and forensic integrity. We use scientific image datasets to assess the performance of neural compression techniques on Visual Question Answering (VQA) and copy-move forgery detection tasks. Our findings indicate that the subtle changes introduced by neural ] compression do not significantly degrade the performance of state-of-the-art solutions. In the experiments, neurally compressed images sufficiently preserved the original semantics and forensic traces. Moreover, compared to lossy techniques, e.g., JPEG compression, at similar bit-per-pixel (bpp) rates, neural compression demonstrates a superior ability to preserve both semantic content and forensic traces, even at high compression levels. Our results suggest that neural compression may provide a viable alternative to lossy compression for scientific images.

Comments

Author Posting © The Author(s), 2025. This article was posted here by permission of ACM for personal use, not for redistribution. This article was published open access in IH&MMSEC '25: Proceedings of the ACM Workshop on Information Hiding and Multimedia Security (June 17, 2025), https://doi.org/10.1145/3733102.3733148.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

Share

COinS