Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, concept erasure methods are studied to facilitate the model to unlearn specific concepts. However, current studies struggle to fully erase malicious concepts implicitly embedded in prompts (e.g., metaphorical expressions or adversarial prompts) while preserving the model's normal generation capability. To address this challenge, our study proposes TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation. Firstly, TRCE starts by erasing the malicious semantics implicitly embedded in textual prompts. By identifying a critical mapping objective(i.e., the [EoT] embedding), we optimize the cross-attention layers to map malicious prompts to contextually similar prompts but with safe concepts. This step prevents the model from being overly influenced by malicious semantics during the denoising process. Following this, considering the deterministic properties of the sampling trajectory of the diffusion model, TRCE further steers the early denoising prediction toward the safe direction and away from the unsafe one through contrastive learning, thus further avoiding the generation of malicious content. Finally, we conduct comprehensive evaluations of TRCE on multiple malicious concept erasure benchmarks, and the results demonstrate its effectiveness in erasing malicious concepts while better preserving the model's original generation ability. The code is available at: http://github.com/ddgoodgood/TRCE. CAUTION: This paper includes model-generated content that may contain offensive material.

翻译：近年来，文本到图像扩散模型的发展使得生成逼真图像成为可能，但它们也存在生成恶意内容（如NSFW图像）的风险。为降低风险，研究者探索了概念擦除方法，以使模型能够遗忘特定概念。然而，现有研究难以在保持模型正常生成能力的同时，完全擦除隐含在提示词中的恶意概念（例如隐喻性表达或对抗性提示）。为应对这一挑战，本研究提出TRCE，采用两阶段概念擦除策略，以实现可靠擦除与知识保留之间的有效平衡。首先，TRCE从擦除文本提示中隐含的恶意语义入手。通过识别一个关键映射目标（即[EoT]嵌入），我们优化交叉注意力层，将恶意提示映射到语境相似但概念安全的提示。这一步骤防止模型在去噪过程中过度受到恶意语义的影响。随后，考虑到扩散模型采样轨迹的确定性特性，TRCE通过对比学习进一步引导早期去噪预测朝向安全方向并远离不安全方向，从而进一步避免恶意内容的生成。最后，我们在多个恶意概念擦除基准上对TRCE进行了全面评估，结果表明其在擦除恶意概念的同时，能更好地保留模型的原始生成能力。代码发布于：http://github.com/ddgoodgood/TRCE。注意：本文包含模型生成的内容，可能涉及冒犯性材料。