The Safety-Aware Denoiser for Text Diffusion Models

• URL: http://arxiv.org/abs/2605.08116v1
• Date: Tue, 28 Apr 2026 00:44:30 GMT
• Title: The Safety-Aware Denoiser for Text Diffusion Models
• Abstract summary: We propose the Safety-Aware Denoiser (SAD), a safety-guidance framework in text diffusion models.<n>SAD modifies the iterative denoising process such that the text sample at the final denoising step is steered toward provably safe regions.<n>We evaluate the safety of the generated text using the SAD, with respect to hazard taxonomy, memorization, and jailbreak.
• Score: 1.6800992804614623
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored. Existing safety approaches are geared toward autoregressive models and typically rely on post-hoc filtering or inference-time interventions. These are inadequate for effectively addressing safety risks in text diffusion models. We propose the Safety-Aware Denoiser (SAD), a safety-guidance framework in text diffusion models. The SAD modifies the iterative denoising process such that the text sample at the final denoising step is steered toward provably safe regions of the text space. This inference-time method can integrate safety constraints into the denoiser, avoiding computationally expensive retraining of the underlying diffusion model and enabling flexible, lightweight safety guidance. We evaluate the safety of the generated text using the SAD, with respect to hazard taxonomy, memorization, and jailbreak. Experimental results show that SAD substantially reduces unsafe generations while preserving generation quality, diversity, and fluency, outperforming existing methods. These results demonstrate that our safety guidance during denoising provides an effective and scalable mechanism for enforcing safety in text diffusion models.

Related papers

• Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models [6.107855416893071]
  Diffusion Language Models (DLMs) provide a promising alternative to autoregressive language models.<n>In this paper, we propose an inference-time defense framework based on the step-wise intervention during the denoising process.<n>Our approaches reduce jailbreak success rates to 0.64% while preserving generation quality close to the original model performance.
  arXiv  Detail & Related papers  (2026-05-13T05:56:45Z)
• A Fragile Guardrail: Diffusion LLM's Safety Blessing and Its Failure Mode [51.43498132808724]
  We show that Diffusion large language models (D-LLMs) have intrinsic robustness against jailbreak attacks.<n>We identify a simple yet effective failure mode, termed context nesting, where harmful requests are embedded within structured benign contexts.<n>We show that this simple strategy is sufficient to bypass D-LLMs' safety blessing, achieving state-of-the-art attack success rates.
  arXiv  Detail & Related papers  (2026-01-30T23:08:14Z)
• SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models [67.84174763413178]
  We introduce SafeRedir, a lightweight inference-time framework for robust unlearning via prompt embedding redirection.<n>We show that SafeRedir achieves effective unlearning capability, high semantic and perceptual preservation, robust image quality, and enhanced resistance to adversarial attacks.
  arXiv  Detail & Related papers  (2026-01-13T15:01:38Z)
• SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress [48.20360860166279]
  We introduce SafeCtrl, a lightweight, non-intrusive plugin that first precisely localizes unsafe content.<n>Instead of performing a hard A-to-B substitution, SafeCtrl then suppresses the harmful semantics, allowing the generative process to naturally and coherently resolve into a safe, context-aware alternative.
  arXiv  Detail & Related papers  (2025-08-16T04:28:52Z)
• Responsible Diffusion Models via Constraining Text Embeddings within Safe Regions [35.28819408507869]
  Concerns have also arisen regarding their potential to produce Not Safe for Work (NSFW) content and exhibit social biases.<n>We propose a novel self-discovery approach to identify a semantic direction vector in the embedding space to restrict text embedding within a safe region.<n>Our method can effectively reduce NSFW content and social bias generated by diffusion models compared to several state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-05-21T12:10:26Z)
• Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization [22.225141381422873]
  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.
  arXiv  Detail & Related papers  (2025-03-19T13:37:52Z)
• Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing [12.986006070964772]
  Safety alignment is an essential research topic for real-world AI applications.<n>Our study first identified the difficulty of eliminating such vulnerabilities without sacrificing the model's helpfulness.<n>Our method could enhance the model's helpfulness while maintaining safety, thus improving the trade-off-front.
  arXiv  Detail & Related papers  (2025-02-04T09:31:54Z)
• 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)
• Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching [74.62818936088065]
  textscSafePatching is a novel framework for comprehensive PSA.<n>textscSafePatching achieves a more comprehensive PSA than baseline methods.<n>textscSafePatching demonstrates its superiority in continual PSA scenarios.
  arXiv  Detail & Related papers  (2024-05-22T16:51:07Z)
• Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts [63.61248884015162]
  Text-to-image diffusion models have shown remarkable ability in high-quality content generation. This work proposes Prompting4 Debugging (P4D) as a tool that automatically finds problematic prompts for diffusion models. Our result shows that around half of prompts in existing safe prompting benchmarks which were originally considered "safe" can actually be manipulated to bypass many deployed safety mechanisms.
  arXiv  Detail & Related papers  (2023-09-12T11:19:36Z)
• 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.