A Training-Free Defense Framework for Robust Learned Image Compression
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914647518478336 |
|---|---|
| author | Song, Myungseo Choi, Jinyoung Han, Bohyung |
| author_facet | Song, Myungseo Choi, Jinyoung Han, Bohyung |
| contents | We study the robustness of learned image compression models against adversarial attacks and present a training-free defense technique based on simple image transform functions. Recent learned image compression models are vulnerable to adversarial attacks that result in poor compression rate, low reconstruction quality, or weird artifacts. To address the limitations, we propose a simple but effective two-way compression algorithm with random input transforms, which is conveniently applicable to existing image compression models. Unlike the naïve approaches, our approach preserves the original rate-distortion performance of the models on clean images. Moreover, the proposed algorithm requires no additional training or modification of existing models, making it more practical. We demonstrate the effectiveness of the proposed techniques through extensive experiments under multiple compression models, evaluation metrics, and attack scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11902 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Training-Free Defense Framework for Robust Learned Image Compression Song, Myungseo Choi, Jinyoung Han, Bohyung Image and Video Processing Computer Vision and Pattern Recognition We study the robustness of learned image compression models against adversarial attacks and present a training-free defense technique based on simple image transform functions. Recent learned image compression models are vulnerable to adversarial attacks that result in poor compression rate, low reconstruction quality, or weird artifacts. To address the limitations, we propose a simple but effective two-way compression algorithm with random input transforms, which is conveniently applicable to existing image compression models. Unlike the naïve approaches, our approach preserves the original rate-distortion performance of the models on clean images. Moreover, the proposed algorithm requires no additional training or modification of existing models, making it more practical. We demonstrate the effectiveness of the proposed techniques through extensive experiments under multiple compression models, evaluation metrics, and attack scenarios. |
| title | A Training-Free Defense Framework for Robust Learned Image Compression |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.11902 |