Text-to-image diffusion models may generate harmful or copyrighted content, motivating research on concept erasure. However, existing approaches primarily focus on erasing concepts from text prompts, overlooking other input modalities that are increasingly critical in real-world applications such as image editing and personalized generation. These modalities can become attack surfaces, where erased concepts re-emerge despite defenses. To bridge this gap, we introduce M-ErasureBench, a novel multimodal evaluation framework that systematically benchmarks concept erasure methods across three input modalities: text prompts, learned embeddings, and inverted latents. For the latter two, we evaluate both white-box and black-box access, yielding five evaluation scenarios. Our analysis shows that existing methods achieve strong erasure performance against text prompts but largely fail under learned embeddings and inverted latents, with Concept Reproduction Rate (CRR) exceeding 90% in the white-box setting. To address these vulnerabilities, we propose IRECE (Inference-time Robustness Enhancement for Concept Erasure), a plug-and-play module that localizes target concepts via cross-attention and perturbs the associated latents during denoising. Experiments demonstrate that IRECE consistently restores robustness, reducing CRR by up to 40% under the most challenging white-box latent inversion scenario, while preserving visual quality. To the best of our knowledge, M-ErasureBench provides the first comprehensive benchmark of concept erasure beyond text prompts. Together with IRECE, our benchmark offers practical safeguards for building more reliable protective generative models.

翻译：文本到图像扩散模型可能生成有害或受版权保护的内容，这推动了概念擦除技术的研究。然而，现有方法主要集中于从文本提示中擦除概念，忽视了在图像编辑和个性化生成等实际应用中日益重要的其他输入模态。这些模态可能成为攻击面，导致已擦除的概念绕过防御而重新出现。为弥补这一空白，我们提出了M-ErasureBench，一种新颖的多模态评估框架，系统性地在三种输入模态上对概念擦除方法进行基准测试：文本提示、学习嵌入和反演潜在表示。针对后两种模态，我们评估了白盒和黑盒访问两种设置，共产生五种评估场景。我们的分析表明，现有方法在应对文本提示时表现出较强的擦除性能，但在学习嵌入和反演潜在表示下大多失效，其中在白盒设置下的概念再现率（CRR）超过90%。为应对这些脆弱性，我们提出了IRECE（推理时概念擦除鲁棒性增强），一种即插即用模块，它通过交叉注意力定位目标概念，并在去噪过程中扰动相关潜在表示。实验表明，IRECE能持续恢复鲁棒性，在最具挑战性的白盒潜在反演场景下将CRR降低达40%，同时保持视觉质量。据我们所知，M-ErasureBench提供了首个超越文本提示的综合性概念擦除基准。结合IRECE，我们的基准为构建更可靠、具备保护性的生成模型提供了实用的安全保障。