Towards properties of adversarial image perturbations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915487980453888 |
|---|---|
| author | Kuznetsov, Egor Aistov, Kirill Koroteev, Maxim |
| author_facet | Kuznetsov, Egor Aistov, Kirill Koroteev, Maxim |
| contents | Using stochastic gradient approach we study the properties of adversarial perturbations resulting in noticeable growth of VMAF image quality metric. The structure of the perturbations is investigated depending on the acceptable PSNR values and based on the Fourier power spectrum computations for the perturbations. It is demonstrated that moderate variation of image brightness ($\sim 10$ pixel units in a restricted region of an image can result in VMAF growth by $\sim 60\%$). Unlike some other methods demonstrating similar VMAF growth, the subjective quality of an image remains almost unchanged. It is also shown that the adversarial perturbations may demonstrate approximately linear dependence of perturbation amplitudes on the image brightness. The perturbations are studied based on the direct VMAF optimization in PyTorch. The significant discrepancies between the metric values and subjective judgements are also demonstrated when image restoration from noise is carried out using the same direct VMAF optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards properties of adversarial image perturbations Kuznetsov, Egor Aistov, Kirill Koroteev, Maxim Computer Vision and Pattern Recognition Using stochastic gradient approach we study the properties of adversarial perturbations resulting in noticeable growth of VMAF image quality metric. The structure of the perturbations is investigated depending on the acceptable PSNR values and based on the Fourier power spectrum computations for the perturbations. It is demonstrated that moderate variation of image brightness ($\sim 10$ pixel units in a restricted region of an image can result in VMAF growth by $\sim 60\%$). Unlike some other methods demonstrating similar VMAF growth, the subjective quality of an image remains almost unchanged. It is also shown that the adversarial perturbations may demonstrate approximately linear dependence of perturbation amplitudes on the image brightness. The perturbations are studied based on the direct VMAF optimization in PyTorch. The significant discrepancies between the metric values and subjective judgements are also demonstrated when image restoration from noise is carried out using the same direct VMAF optimization. |
| title | Towards properties of adversarial image perturbations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.14111 |