TraSCE: Trajectory Steering for Concept Erasure

• URL: http://arxiv.org/abs/2412.07658v1
• Date: Tue, 10 Dec 2024 16:45:03 GMT
• Title: TraSCE: Trajectory Steering for Concept Erasure
• Authors: Anubhav Jain, Yuya Kobayashi, Takashi Shibuya, Yuhta Takida, Nasir Memon, Julian Togelius, Yuki Mitsufuji,
• Abstract summary: Text-to-image diffusion models have been shown to generate harmful content such as not-safe-for-work (NSFW) images. We propose TraSCE, an approach to guide the diffusion trajectory away from generating harmful content.
• Score: 16.752023123940674
• License:
• Abstract: Recent advancements in text-to-image diffusion models have brought them to the public spotlight, becoming widely accessible and embraced by everyday users. However, these models have been shown to generate harmful content such as not-safe-for-work (NSFW) images. While approaches have been proposed to erase such abstract concepts from the models, jail-breaking techniques have succeeded in bypassing such safety measures. In this paper, we propose TraSCE, an approach to guide the diffusion trajectory away from generating harmful content. Our approach is based on negative prompting, but as we show in this paper, conventional negative prompting is not a complete solution and can easily be bypassed in some corner cases. To address this issue, we first propose a modification of conventional negative prompting. Furthermore, we introduce a localized loss-based guidance that enhances the modified negative prompting technique by steering the diffusion trajectory. We demonstrate that our proposed method achieves state-of-the-art results on various benchmarks in removing harmful content including ones proposed by red teams; and erasing artistic styles and objects. Our proposed approach does not require any training, weight modifications, or training data (both image or prompt), making it easier for model owners to erase new concepts.

Related papers

• ACE: Anti-Editing Concept Erasure in Text-to-Image Models [73.00930293474009]
  Existing concept erasure methods achieve superior results in preventing the production of erased concept from prompts. We propose an Anti-Editing Concept Erasure (ACE) method, which not only erases the target concept during generation but also filters out it during editing.
  arXiv  Detail & Related papers  (2025-01-03T04:57:27Z)
• Continuous Concepts Removal in Text-to-image Diffusion Models [27.262721132177845]
  Concerns have been raised about the potential for text-to-image models to create content that infringes on copyrights or depicts disturbing subject matter. We propose a novel approach called CCRT that includes a designed knowledge distillation paradigm. It constrains the text-image alignment behavior during the continuous concept removal process by using a set of text prompts.
  arXiv  Detail & Related papers  (2024-11-30T20:40:10Z)
• Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models [57.16056181201623]
  Fine-tuning text-to-image diffusion models can inadvertently undo safety measures, causing models to relearn harmful concepts. We present a novel but immediate solution called Modular LoRA, which involves training Safety Low-Rank Adaptation modules separately from Fine-Tuning LoRA components. This method effectively prevents the re-learning of harmful content without compromising the model's performance on new tasks.
  arXiv  Detail & Related papers  (2024-11-30T04:37:38Z)
• Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models [35.2881940850787]
  Text-to-image diffusion models inadvertently learn inappropriate concepts from vast and unfiltered training data. Our method effectively captures the manifestation of subtle words at the image level, enabling direct and efficient erasure of target concepts.
  arXiv  Detail & Related papers  (2024-08-02T05:17:14Z)
• Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models [76.39651111467832]
  We introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. To mitigate inappropriate content potentially represented by derived embeddings, RECE aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts.
  arXiv  Detail & Related papers  (2024-07-17T08:04:28Z)
• Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion [51.931083971448885]
  We propose a framework named Human Feedback Inversion (HFI), where human feedback on model-generated images is condensed into textual tokens guiding the mitigation or removal of problematic images. Our experimental results demonstrate our framework significantly reduces objectionable content generation while preserving image quality, contributing to the ethical deployment of AI in the public sphere.
  arXiv  Detail & Related papers  (2024-07-17T05:21:41Z)
• Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models [58.74606272936636]
  Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. The models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. concept removal methods have been proposed to modify diffusion models to prevent the generation of malicious and unwanted concepts.
  arXiv  Detail & Related papers  (2024-06-21T03:58:44Z)
• Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models [63.20512617502273]
  We propose a method called SDD to prevent problematic content generation in text-to-image diffusion models. Our method eliminates a much greater proportion of harmful content from the generated images without degrading the overall image quality.
  arXiv  Detail & Related papers  (2023-07-12T07:48:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.