Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.05490 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914972528803840 |
|---|---|
| author | Hofer, Nora Böhme, Rainer |
| author_facet | Hofer, Nora Böhme, Rainer |
| contents | Neural compression has the potential to revolutionize lossy image compression. Based on generative models, recent schemes achieve unprecedented compression rates at high perceptual quality but compromise semantic fidelity. Details of decompressed images may appear optically flawless but semantically different from the originals, making compression errors difficult or impossible to detect. We explore the problem space and propose a provisional taxonomy of miscompressions. It defines three types of 'what happens' and has a binary 'high impact' flag indicating miscompressions that alter symbols. We discuss how the taxonomy can facilitate risk communication and research into mitigations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05490 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Taxonomy of Miscompressions: Preparing Image Forensics for Neural Compression Hofer, Nora Böhme, Rainer Cryptography and Security Computer Vision and Pattern Recognition Neural compression has the potential to revolutionize lossy image compression. Based on generative models, recent schemes achieve unprecedented compression rates at high perceptual quality but compromise semantic fidelity. Details of decompressed images may appear optically flawless but semantically different from the originals, making compression errors difficult or impossible to detect. We explore the problem space and propose a provisional taxonomy of miscompressions. It defines three types of 'what happens' and has a binary 'high impact' flag indicating miscompressions that alter symbols. We discuss how the taxonomy can facilitate risk communication and research into mitigations. |
| title | A Taxonomy of Miscompressions: Preparing Image Forensics for Neural Compression |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.05490 |