PromptLA: Towards Integrity Verification of Black-box Text-to-Image Diffusion Models

• URL: http://arxiv.org/abs/2412.16257v1
• Date: Fri, 20 Dec 2024 07:24:32 GMT
• Title: PromptLA: Towards Integrity Verification of Black-box Text-to-Image Diffusion Models
• Authors: Zhuomeng Zhang, Fangqi Li, Chong Di, Shilin Wang,
• Abstract summary: Current text-to-image (T2I) diffusion models can produce high-quality images. Malicious users who are authorized to use the model only for benign purposes might modify their models to generate images that result in harmful social impacts. We propose a novel prompt selection algorithm for efficient and accurate integrity verification of T2I diffusion models.
• Score: 16.67563247104523
• License:
• Abstract: Current text-to-image (T2I) diffusion models can produce high-quality images, and malicious users who are authorized to use the model only for benign purposes might modify their models to generate images that result in harmful social impacts. Therefore, it is essential to verify the integrity of T2I diffusion models, especially when they are deployed as black-box services. To this end, considering the randomness within the outputs of generative models and the high costs in interacting with them, we capture modifications to the model through the differences in the distributions of the features of generated images. We propose a novel prompt selection algorithm based on learning automaton for efficient and accurate integrity verification of T2I diffusion models. Extensive experiments demonstrate the effectiveness, stability, accuracy and generalization of our algorithm against existing integrity violations compared with baselines. To the best of our knowledge, this paper is the first work addressing the integrity verification of T2I diffusion models, which paves the way to copyright discussions and protections for artificial intelligence applications in practice.

Related papers

• SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models [77.80595722480074]
  SleeperMark is a novel framework designed to embed resilient watermarks into T2I diffusion models. It guides the model to disentangle the watermark information from the semantic concepts it learns, allowing the model to retain the embedded watermark. Our experiments demonstrate the effectiveness of SleeperMark across various types of diffusion models.
  arXiv  Detail & Related papers  (2024-12-06T08:44:18Z)
• Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation [4.1364578693016325]
  Uncertainty quantification in text-to-image (T2I) generative models is crucial for understanding model behavior and improving output reliability. We are the first to quantify and evaluate the uncertainty of T2I models with respect to the prompt. We introduce Prompt-based UNCertainty Estimation for T2I models (PUNC) to better address uncertainties arising from the semantics of the prompt and generated images.
  arXiv  Detail & Related papers  (2024-12-04T10:03:52Z)
• Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models [54.052963634384945]
  We introduce the Image Regeneration task to assess text-to-image models. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model. We also present ImageRepainter framework to enhance the quality of generated images.
  arXiv  Detail & Related papers  (2024-11-14T13:52:43Z)
• Model Integrity when Unlearning with T2I Diffusion Models [11.321968363411145]
  We propose approximate Machine Unlearning algorithms to reduce the generation of specific types of images, characterized by samples from a forget distribution'' We then propose unlearning algorithms that demonstrate superior effectiveness in preserving model integrity compared to existing baselines.
  arXiv  Detail & Related papers  (2024-11-04T13:15:28Z)
• Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending [54.26862913139299]
  We introduce a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB) TEAWIB incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models. Experiments validate the effectiveness of TEAWIB, showcasing the state-of-the-art performance in perceptual quality and attribution accuracy.
  arXiv  Detail & Related papers  (2024-09-17T07:52:09Z)
• Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models [20.70550870149442]
  We introduce Annealed Importance Guidance (AIG), an inference-time regularization inspired by Annealed Importance Sampling. Our experiments demonstrate the benefits of AIG for Stable Diffusion models, striking the optimal balance between reward optimization and image diversity.
  arXiv  Detail & Related papers  (2024-09-09T16:27:26Z)
• Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion [21.252145402613472]
  This work addresses the challenge of quantifying originality in text-to-image (T2I) generative diffusion models. We propose a method that leverages textual inversion to measure the originality of an image based on the number of tokens required for its reconstruction by the model.
  arXiv  Detail & Related papers  (2024-08-15T14:42:02Z)
• Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation [59.184980778643464]
  Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI) In this paper, we introduce an innovative technique called self-play fine-tuning for diffusion models (SPIN-Diffusion) Our approach offers an alternative to conventional supervised fine-tuning and RL strategies, significantly improving both model performance and alignment.
  arXiv  Detail & Related papers  (2024-02-15T18:59:18Z)
• Harnessing Diffusion Models for Visual Perception with Meta Prompts [68.78938846041767]
  We propose a simple yet effective scheme to harness a diffusion model for visual perception tasks. We introduce learnable embeddings (meta prompts) to the pre-trained diffusion models to extract proper features for perception. Our approach achieves new performance records in depth estimation tasks on NYU depth V2 and KITTI, and in semantic segmentation task on CityScapes.
  arXiv  Detail & Related papers  (2023-12-22T14:40:55Z)
• SinDiffusion: Learning a Diffusion Model from a Single Natural Image [159.4285444680301]
  We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image. It is based on two core designs. First, SinDiffusion is trained with a single model at a single scale instead of multiple models with progressive growing of scales. Second, we identify that a patch-level receptive field of the diffusion network is crucial and effective for capturing the image's patch statistics.
  arXiv  Detail & Related papers  (2022-11-22T18:00:03Z)

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.