通过对抗性交叉注意力使图像免受文本到图像编辑的影响
Immunizing Images from Text to Image Editing via Adversarial Cross-Attention
AI总结：
提出Attention Attack对抗攻击，通过破坏文本提示与图像视觉表示间的交叉注意力，使图像免受文本到图像编辑影响，并引入Caption Similarity和语义IoU两种新评估策略验证其有效性。
摘要：
近期基于文本的图像编辑技术进展，实现了由自然语言引导的视觉内容细粒度操控。然而，此类方法易受对抗攻击影响。本工作提出一种针对编辑方法视觉组件的新型攻击。我们引入Attention Attack，通过使用源图像自动生成的描述作为编辑提示的代理，破坏文本提示与图像视觉表示之间的交叉注意力。此方法无需了解编辑方法或编辑提示，即可打破图像内容与其文本描述间的对齐。针对现有免疫成功度指标的可靠性，我们提出两种新评估策略：Caption Similarity，量化原始编辑与对抗编辑间的语义一致性；语义交并比（IoU），通过分割掩码测量空间布局破坏程度。在TEDBench++基准上的实验表明，我们的攻击在保持不可感知的同时显著降低了编辑性能。
英文摘要：
Recent advances in text-based image editing have enabled fine-grained manipulation of visual content guided by natural language. However, such methods are susceptible to adversarial attacks. In this work, we propose a novel attack that targets the visual component of editing methods. We introduce Attention Attack, which disrupts the cross-attention between a textual prompt and the visual representation of the image by using an automatically generated caption of the source image as a proxy for the edit prompt. This breaks the alignment between the contents of the image and their textual description, without requiring knowledge of the editing method or the editing prompt. Reflecting on the reliability of existing metrics for immunization success, we propose two novel evaluation strategies: Caption Similarity, which quantifies semantic consistency between original and adversarial edits, and semantic Intersection over Union (IoU), which measures spatial layout disruption via segmentation masks. Experiments conducted on the TEDBench++ benchmark demonstrate that our attack significantly degrades editing performance while remaining imperceptible.
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。
