T-MLA: A targeted multiscale log-exponential attack framework for neural image compression
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917240196038656 |
|---|---|
| author | Kalmykov, Nikolay I. Dibo, Razan Shen, Kaiyu Zhonghan, Xu Phan, Anh-Huy Liu, Yipeng Oseledets, Ivan |
| author_facet | Kalmykov, Nikolay I. Dibo, Razan Shen, Kaiyu Zhonghan, Xu Phan, Anh-Huy Liu, Yipeng Oseledets, Ivan |
| contents | Neural image compression (NIC) has become the state-of-the-art for rate-distortion performance, yet its security vulnerabilities remain significantly less understood than those of classifiers. Existing adversarial attacks on NICs are often naive adaptations of pixel-space methods, overlooking the unique, structured nature of the compression pipeline. In this work, we propose a more advanced class of vulnerabilities by introducing T-MLA, the first targeted multiscale log-exponential attack framework. We introduce adversarial perturbations in the wavelet domain that concentrate on less perceptually salient coefficients, improving the stealth of the attack. Extensive evaluation across multiple state-of-the-art NIC architectures on standard image compression benchmarks reveals a large drop in reconstruction quality while the perturbations remain visually imperceptible. On standard NIC benchmarks, T-MLA achieves targeted degradation of reconstruction quality while improving perturbation imperceptibility (higher PSNR/VIF of the perturbed inputs) compared to PGD-style baselines at comparable attack success, as summarized in our main results. Our findings reveal a critical security flaw at the core of generative and content delivery pipelines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01079 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | T-MLA: A targeted multiscale log-exponential attack framework for neural image compression Kalmykov, Nikolay I. Dibo, Razan Shen, Kaiyu Zhonghan, Xu Phan, Anh-Huy Liu, Yipeng Oseledets, Ivan Computer Vision and Pattern Recognition Numerical Analysis Neural image compression (NIC) has become the state-of-the-art for rate-distortion performance, yet its security vulnerabilities remain significantly less understood than those of classifiers. Existing adversarial attacks on NICs are often naive adaptations of pixel-space methods, overlooking the unique, structured nature of the compression pipeline. In this work, we propose a more advanced class of vulnerabilities by introducing T-MLA, the first targeted multiscale log-exponential attack framework. We introduce adversarial perturbations in the wavelet domain that concentrate on less perceptually salient coefficients, improving the stealth of the attack. Extensive evaluation across multiple state-of-the-art NIC architectures on standard image compression benchmarks reveals a large drop in reconstruction quality while the perturbations remain visually imperceptible. On standard NIC benchmarks, T-MLA achieves targeted degradation of reconstruction quality while improving perturbation imperceptibility (higher PSNR/VIF of the perturbed inputs) compared to PGD-style baselines at comparable attack success, as summarized in our main results. Our findings reveal a critical security flaw at the core of generative and content delivery pipelines. |
| title | T-MLA: A targeted multiscale log-exponential attack framework for neural image compression |
| topic | Computer Vision and Pattern Recognition Numerical Analysis |
| url | https://arxiv.org/abs/2511.01079 |