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. Our approach crafts adversarial perturbations in the wavelet domain by directly targeting the quality of the attacked and reconstructed images. This allows for a principled, offline attack where perturbations are strategically confined to specific wavelet subbands, maximizing distortion while ensuring perceptual stealth. 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. Our findings reveal a critical security flaw at the core of generative and content delivery pipelines.
翻译:神经图像压缩(NIC)已成为率失真性能的先进技术,但其安全漏洞的理解程度远低于分类器。现有针对NIC的对抗攻击通常是对像素空间方法的简单移植,忽略了压缩流水线独特的结构化特性。在本工作中,我们通过提出T-MLA——首个定向多尺度对数-指数攻击框架,揭示了一类更为高级的漏洞。该方法在频域中通过直接针对攻击后重建图像的质量来构造对抗扰动,实现了一种原理性、离线的攻击策略,将扰动策略性地限制在特定子带内,在最大化失真的同时确保感知隐蔽性。在标准图像压缩基准上对多种先进NIC架构的广泛评估表明,重建质量显著下降,而扰动在视觉上仍难以察觉。我们的研究揭示了生成式与内容分发流水线核心存在的关键安全缺陷。