一种用于抵御恶意视觉操纵的知识引导对抗防御
A Knowledge-guided Adversarial Defense for Resisting Malicious Visual Manipulation
AI总结：
针对现有对抗防御方法在低级特征空间扭曲伪造样本的局限性，提出知识引导的对抗防御（KGAD），通过在领域知识层面构建语义混淆并引入视觉感知度量，迫使恶意操纵模型输出语义混淆样本，在两项任务中表现优于现有方法且泛化性强。
摘要：
视觉操纵的恶意应用在许多领域对用户的安全和声誉造成了严重威胁。为了缓解这些问题，近年来基于对抗噪声的防御方法得到了热烈的研究。然而，“仅依赖数据”的方法倾向于在低级特征空间而非高级语义空间中扭曲伪造样本，导致在抵御恶意操纵方面存在局限性。前沿研究表明，在深度学习中整合知识可以产生可靠且具有泛化能力的解决方案。受此启发，我们提出了一种知识引导的对抗防御（KGAD），以主动迫使恶意操纵模型输出语义混淆的样本。具体而言，在生成对抗噪声的过程中，我们专注于在领域特定知识层面构建显著的语义混淆，并利用与视觉感知密切相关的度量来替代通用的逐像素度量。生成的对抗噪声能够通过在伪造样本中触发知识引导和感知相关的破坏，主动干扰恶意操纵模型。为了验证所提方法的有效性，我们在人类感知和视觉质量评估上进行了定性和定量实验。在两个不同任务上的结果均表明，与最先进的方法相比，我们的防御提供了更好的保护，并实现了极大的泛化能力。
英文摘要：
Malicious applications of visual manipulation have raised serious threats to the security and reputation of users in many fields. To alleviate these issues, adversarial noise-based defenses have been enthusiastically studied in recent years. However, ``data-only" methods tend to distort fake samples in the low-level feature space rather than the high-level semantic space, leading to limitations in resisting malicious manipulation. Frontier research has shown that integrating knowledge in deep learning can produce reliable and generalizable solutions. Inspired by these, we propose a knowledge-guided adversarial defense (KGAD) to actively force malicious manipulation models to output semantically confusing samples. Specifically, in the process of generating adversarial noise, we focus on constructing significant semantic confusions at the domain-specific knowledge level, and exploit a metric closely related to visual perception to replace the general pixel-wise metrics. The generated adversarial noise can actively interfere with the malicious manipulation model by triggering knowledge-guided and perception-related disruptions in the fake samples. To validate the effectiveness of the proposed method, we conduct qualitative and quantitative experiments on human perception and visual quality assessment. The results on two different tasks both show that our defense provides better protection compared to state-of-the-art methods and achieves great generalizability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
