Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization

• URL: http://arxiv.org/abs/2503.15197v1
• Date: Wed, 19 Mar 2025 13:37:52 GMT
• Title: Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
• Authors: Feifei Li, Mi Zhang, Yiming Sun, Min Yang,
• Abstract summary: There is a growing concern about text-to-image diffusion models creating harmful content.<n>Post-hoc model intervention techniques, such as concept unlearning and safety guidance, have been developed to mitigate these risks.<n>We propose the safe generation framework Detect-and-Guide (DAG) to perform self-diagnosis and fine-interpret self-regulation.<n>DAG achieves state-of-the-art safe generation performance, balancing harmfulness mitigation and text-following performance on real-world prompts.
• Score: 22.225141381422873
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image diffusion models have achieved state-of-the-art results in synthesis tasks; however, there is a growing concern about their potential misuse in creating harmful content. To mitigate these risks, post-hoc model intervention techniques, such as concept unlearning and safety guidance, have been developed. However, fine-tuning model weights or adapting the hidden states of the diffusion model operates in an uninterpretable way, making it unclear which part of the intermediate variables is responsible for unsafe generation. These interventions severely affect the sampling trajectory when erasing harmful concepts from complex, multi-concept prompts, thus hindering their practical use in real-world settings. In this work, we propose the safe generation framework Detect-and-Guide (DAG), leveraging the internal knowledge of diffusion models to perform self-diagnosis and fine-grained self-regulation during the sampling process. DAG first detects harmful concepts from noisy latents using refined cross-attention maps of optimized tokens, then applies safety guidance with adaptive strength and editing regions to negate unsafe generation. The optimization only requires a small annotated dataset and can provide precise detection maps with generalizability and concept specificity. Moreover, DAG does not require fine-tuning of diffusion models, and therefore introduces no loss to their generation diversity. Experiments on erasing sexual content show that DAG achieves state-of-the-art safe generation performance, balancing harmfulness mitigation and text-following performance on multi-concept real-world prompts.

Related papers

• 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.<n>We present a novel but immediate solution called Modular LoRA, which involves training Safety Low-Rank Adaptation modules separately from Fine-Tuning LoRA components.<n>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)
• Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction [88.18235230849554]
  Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs.<n>We leverage safe embeddings and a modified diffusion process with weighted tunable summation in the latent space to generate safer images.<n>We identify trade-offs between safety and censorship, which presents a necessary perspective in the development of ethical AI models.
  arXiv  Detail & Related papers  (2024-11-21T09:47:13Z)
• Transferable Adversarial Attacks on SAM and Its Downstream Models [87.23908485521439]
  This paper explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM) To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm.
  arXiv  Detail & Related papers  (2024-10-26T15:04:04Z)
• Perturb, Attend, Detect and Localize (PADL): Robust Proactive Image Defense [5.150608040339816]
  We introduce PADL, a new solution able to generate image-specific perturbations using a symmetric scheme of encoding and decoding based on cross-attention. Our method generalizes to a range of unseen models with diverse architectural designs, such as StarGANv2, BlendGAN, DiffAE, StableDiffusion and StableDiffusionXL.
  arXiv  Detail & Related papers  (2024-09-26T15:16:32Z)
• Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks [41.531913152661296]
  We formulate the problem of targeted adversarial attack on Stable Diffusion and propose a framework to generate adversarial prompts. Specifically, we design a gradient-based embedding optimization method to craft reliable adversarial prompts that guide stable diffusion to generate specific images. After obtaining successful adversarial prompts, we reveal the mechanisms that cause the vulnerability of the model.
  arXiv  Detail & Related papers  (2024-01-16T12:15:39Z)
• Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model [61.53213964333474]
  We propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness.
  arXiv  Detail & Related papers  (2023-12-18T15:25:23Z)
• Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models? [52.238883592674696]
  Ring-A-Bell is a model-agnostic red-teaming tool for T2I diffusion models. It identifies problematic prompts for diffusion models with the corresponding generation of inappropriate content. Our results show that Ring-A-Bell, by manipulating safe prompting benchmarks, can transform prompts that were originally regarded as safe to evade existing safety mechanisms.
  arXiv  Detail & Related papers  (2023-10-16T02:11:20Z)
• LEAT: Towards Robust Deepfake Disruption in Real-World Scenarios via Latent Ensemble Attack [11.764601181046496]
  Deepfakes, malicious visual contents created by generative models, pose an increasingly harmful threat to society. To proactively mitigate deepfake damages, recent studies have employed adversarial perturbation to disrupt deepfake model outputs. We propose a simple yet effective disruption method called Latent Ensemble ATtack (LEAT), which attacks the independent latent encoding process.
  arXiv  Detail & Related papers  (2023-07-04T07:00:37Z)
• SafeDiffuser: Safe Planning with Diffusion Probabilistic Models [97.80042457099718]
  Diffusion model-based approaches have shown promise in data-driven planning, but there are no safety guarantees. We propose a new method, called SafeDiffuser, to ensure diffusion probabilistic models satisfy specifications. We test our method on a series of safe planning tasks, including maze path generation, legged robot locomotion, and 3D space manipulation.
  arXiv  Detail & Related papers  (2023-05-31T19:38:12Z)

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.