SteerDiff: Steering towards Safe Text-to-Image Diffusion Models

• URL: http://arxiv.org/abs/2410.02710v1
• Date: Thu, 3 Oct 2024 17:34:55 GMT
• Title: SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
• Authors: Hongxiang Zhang, Yifeng He, Hao Chen,
• Abstract summary: Text-to-image (T2I) diffusion models can be misused to produce inappropriate content. We introduce SteerDiff, a lightweight adaptor module designed to act as an intermediary between user input and the diffusion model. We conduct extensive experiments across various concept unlearning tasks to evaluate the effectiveness of our approach.
• Score: 5.781285400461636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused to produce inappropriate content. Existing safety measures, which typically rely on text classifiers or ControlNet-like approaches, are often insufficient. Traditional text classifiers rely on large-scale labeled datasets and can be easily bypassed by rephrasing. As diffusion models continue to scale, fine-tuning these safeguards becomes increasingly challenging and lacks flexibility. Recent red-teaming attack researches further underscore the need for a new paradigm to prevent the generation of inappropriate content. In this paper, we introduce SteerDiff, a lightweight adaptor module designed to act as an intermediary between user input and the diffusion model, ensuring that generated images adhere to ethical and safety standards with little to no impact on usability. SteerDiff identifies and manipulates inappropriate concepts within the text embedding space to guide the model away from harmful outputs. We conduct extensive experiments across various concept unlearning tasks to evaluate the effectiveness of our approach. Furthermore, we benchmark SteerDiff against multiple red-teaming strategies to assess its robustness. Finally, we explore the potential of SteerDiff for concept forgetting tasks, demonstrating its versatility in text-conditioned image generation.

Related papers

• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [49.60774626839712]
  multimodal generative models have sparked critical discussions on their fairness, reliability, and potential for misuse. We propose an evaluation framework designed to assess model reliability through their responses to perturbations in the embedding space. Our method lays the groundwork for detecting unreliable, bias-injected models and retrieval of bias provenance.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• Adversarial Robustification via Text-to-Image Diffusion Models [56.37291240867549]
  Adrial robustness has been conventionally believed as a challenging property to encode for neural networks. We develop a scalable and model-agnostic solution to achieve adversarial robustness without using any data.
  arXiv  Detail & Related papers  (2024-07-26T10:49:14Z)
• EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations [73.94175015918059]
  We introduce a novel approach, EnTruth, which Enhances Traceability of unauthorized dataset usage. By strategically incorporating the template memorization, EnTruth can trigger the specific behavior in unauthorized models as the evidence of infringement. Our method is the first to investigate the positive application of memorization and use it for copyright protection, which turns a curse into a blessing.
  arXiv  Detail & Related papers  (2024-06-20T02:02:44Z)
• Learning to Generate Training Datasets for Robust Semantic Segmentation [37.9308918593436]
  We propose a novel approach to improve the robustness of semantic segmentation techniques. We design Robusta, a novel conditional generative adversarial network to generate realistic and plausible perturbed images. Our results suggest that this approach could be valuable in safety-critical applications.
  arXiv  Detail & Related papers  (2023-08-01T10:02:26Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography [15.705627450233504]
  We propose a novel image steganography framework, named Controllable, Robust and Secure Image Steganography (CRoSS) CRoSS has significant advantages in controllability, robustness, and security compared to cover-based image steganography methods.
  arXiv  Detail & Related papers  (2023-05-26T13:52:57Z)
• Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models [103.61066310897928]
  Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt. While revolutionary, current state-of-the-art diffusion models may still fail in generating images that fully convey the semantics in the given text prompt. We analyze the publicly available Stable Diffusion model and assess the existence of catastrophic neglect, where the model fails to generate one or more of the subjects from the input prompt. We introduce the concept of Generative Semantic Nursing (GSN), where we seek to intervene in the generative process on the fly during inference time to improve the faithfulness
  arXiv  Detail & Related papers  (2023-01-31T18:10:38Z)

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.