概念替换技术真的能擦除不可接受概念吗？
Do Concept Replacement Techniques Really Erase Unacceptable Concepts?
AI总结：
本文揭示现有概念替换技术在 I2I 场景中无法真正擦除不可接受概念，提出应同时保证擦除有效性与其他概念保真度，并给出定向图像编辑方法 AntiMirror。
摘要：
生成模型，尤其是基于扩散的文本到图像（T2I）模型，已经取得了令人瞩目的成功。然而，使它们对齐以避免生成包含不可接受概念（例如冒犯性或受版权保护的内容，或名人肖像）的内容，仍然是一项重大挑战。概念替换技术（CRT）旨在应对这一挑战，通常通过尝试从模型中“擦除”不可接受概念来实现。最近，模型提供商开始提供图像编辑服务，这类服务接收图像和文本提示作为输入，以生成按照提示指定方式修改后的图像。这些模型被称为图像到图像（I2I）模型。在本文中，我们首先使用一个 I2I 模型通过实验证明，当今最先进的 CRT 实际上并没有擦除不可接受概念。因此，尽管现有 CRT 已被证明能够在 T2I 流程中移除不需要的概念，但它们在新兴的 I2I 场景中可能是无效的，这凸显出有必要理解 T2I 与 I2I 设置之间的这种差异。接下来，我们认为，一个好的 CRT 在替换不可接受概念的同时，应当保留生成模型输入中指定的其他概念。我们将此称为保真度。以往关于 CRT 的工作忽视了涉及不可接受概念时的保真度。最后，我们提出使用有针对性的图像编辑技术来同时实现有效性和保真度。我们提出了这样一种技术 AntiMirror，并证明了其可行性。
英文摘要：
Generative models, particularly diffusion-based text-to-image (T2I) models, have demonstrated astounding success. However, aligning them to avoid generating content with unacceptable concepts (e.g., offensive or copyrighted content, or celebrity likenesses) remains a significant challenge. Concept replacement techniques (CRTs) aim to address this challenge, often by trying to "erase" unacceptable concepts from models. Recently, model providers have started offering image editing services which accept an image and a text prompt as input, to produce an image altered as specified by the prompt. These are known as image-to-image (I2I) models. In this paper, we first use an I2I model to empirically demonstrate that today's state-of-the-art CRTs do not in fact erase unacceptable concepts. Existing CRTs are thus likely to be ineffective in emerging I2I scenarios, despite their proven ability to remove unwanted concepts in T2I pipelines, highlighting the need to understand this discrepancy between T2I and I2I settings. Next, we argue that a good CRT, while replacing unacceptable concepts, should preserve other concepts specified in the inputs to generative models. We call this fidelity. Prior work on CRTs have neglected fidelity in the case of unacceptable concepts. Finally, we propose the use of targeted image-editing techniques to achieve both effectiveness and fidelity. We present such a technique, AntiMirror, and demonstrate its viability.
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。
