Disciplined Diffusion: Text-to-Image Diffusion Model against NSFW Generation

• URL: http://arxiv.org/abs/2605.01113v1
• Date: Fri, 01 May 2026 21:33:06 GMT
• Title: Disciplined Diffusion: Text-to-Image Diffusion Model against NSFW Generation
• Abstract summary: Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts.<n>They pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs.<n>We propose Disciplined Diffusion (DDiffusion), a novel robust text-to-image diffusion that counters Not Safe For Work (NSFW) generation.
• Score: 9.862349752373577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturbing imagery when provided with harmful inputs. Existing safety filters typically rely on text-based classifiers or image-based checkers that completely block the output upon detecting a threat, issuing an explicit allow/block feedback signal to the user. This binary strategy leaves models vulnerable to adversarial attacks that alter keywords to bypass detection, and it causes high false-alarm rates that degrade the experience for benign users. To address such vulnerabilities, we propose Disciplined Diffusion (DDiffusion), a novel robust text-to-image diffusion that counters Not Safe For Work (NSFW) generation by uncovering implicit malicious semantics in prompt embeddings. DDiffusion leverages a semantic retrieval mechanism to evaluate prompts against concept distributions rather than relying on brittle pairwise similarity. Furthermore, it employs a localization method during the diffusion process to selectively edit only the harmful regions of the generated image. By returning locally sanitized images instead of applying uniform blocking, DDiffusion suppresses malicious content while preserving generation fidelity for benign prompts and avoiding the binary allow-deny signal on which existing probing attacks rely.

Related papers

• Automatic Red Teaming for Implicit Vulnerabilities of Text-to-Image Models [58.59008920408855]
  We propose Adversarial Probing for Implicit VulnErabilities (AdvPIE) to expose implicit vulnerabilities without requiring access to the parameters of target models.<n> AdvPIE adopts a policy agent to generate and refine implicit adversarial prompts based on the feedback from a judge agent.<n>Experiments on standard and safety-aligned T2I models show that AdvPIE1 effectively uncovers implicit vulnerabilities.
  arXiv  Detail & Related papers  (2026-09-05T13:45:09Z)
• Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation [74.5813283875938]
  Zero-shot image-to-image generation poses substantial risks related to intellectual property violations.<n>This work presents Adapter Shield, the first universal and authentication-integrated solution aimed at defending personal images from misuse.<n>Our method surpasses existing state-of-the-art defenses in blocking unauthorized zero-shot image synthesis.
  arXiv  Detail & Related papers  (2025-11-25T04:49:16Z)
• Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models [73.43013217318965]
  Multimodal Prompt Decoupling Attack (MPDA)<n>MPDA uses image modality to separate the harmful semantic components of the original unsafe prompt.<n>Visual language model generates image captions to ensure semantic consistency between the generated NSFW images and the original unsafe prompts.
  arXiv  Detail & Related papers  (2025-09-21T11:22:32Z)
• PromptFlare: Prompt-Generalized Defense via Cross-Attention Decoy in Diffusion-Based Inpainting [25.24109316946351]
  We propose PromptFlare, a novel adversarial protection method designed to protect images from malicious modifications facilitated by diffusion-based inpainting models.<n>Our approach exploits the intrinsic properties of prompt embeddings and injects adversarial noise to suppress the sampling process.<n>Experiments on the EditBench dataset demonstrate that our method achieves state-of-the-art performance across various metrics.
  arXiv  Detail & Related papers  (2025-08-22T08:42:46Z)
• Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models [70.03122709795122]
  Backdoor attacks targeting text-to-image diffusion models have advanced rapidly.<n>Current backdoor samples often exhibit two key abnormalities compared to benign samples.<n>We propose Trigger without Trace (TwT) by explicitly mitigating these consistencies.
  arXiv  Detail & Related papers  (2025-03-22T10:41:46Z)
• TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models [53.937498564603054]
  Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images.<n>To mitigate risk, concept erasure methods are studied to facilitate the model to unlearn specific concepts.<n>We propose TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation.
  arXiv  Detail & Related papers  (2025-03-10T14:37:53Z)
• Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models [2.2917707112773593]
  Distorting Embedding Space (DES) is a text encoder-based defense mechanism.<n>DES transforms unsafe embeddings, extracted from a text encoder using unsafe prompts, toward carefully calculated safe embedding regions.<n>DES also neutralizes the nudity'' embedding, by aligning it with neutral embedding to enhance robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2025-01-31T04:14:05Z)
• SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack [13.799517170191919]
  Recent research has shown that safety checkers have vulnerabilities against adversarial attacks, allowing them to generate Not Safe For Work (NSFW) images.<n>We propose SC-Pro, a training-free framework that easily defends against adversarial attacks generating NSFW images.
  arXiv  Detail & Related papers  (2025-01-09T16:43:21Z)
• AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models [33.29825481203704]
  AdvI2I is a novel framework that manipulates input images to induce diffusion models to generate NSFW content.<n>By optimizing a generator to craft adversarial images, AdvI2I circumvents existing defense mechanisms.<n>We show that both AdvI2I and AdvI2I-Adaptive can effectively bypass current safeguards.
  arXiv  Detail & Related papers  (2024-10-28T19:15:06Z)
• Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization [19.635385099376066]
  malicious users have misused diffusion-based customization methods like DreamBooth to create fake images. In this paper, we propose DisDiff, a novel adversarial attack method to disrupt the diffusion model outputs.
  arXiv  Detail & Related papers  (2024-05-31T02:45:31Z)
• Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models [10.70975463369742]
  We present the Jailbreaking Prompt Attack (JPA)<n>JPA searches for the target malicious concepts in the text embedding space using a group of antonyms.<n>A prefix prompt is optimized in the discrete vocabulary space to align malicious concepts semantically in the text embedding space.
  arXiv  Detail & Related papers  (2024-04-02T09:49:35Z)
• 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)
• IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI [52.90082445349903]
  Diffusion-based image generation models can create artistic images that mimic the style of an artist or maliciously edit the original images for fake content. Several attempts have been made to protect the original images from such unauthorized data usage by adding imperceptible perturbations. In this work, we introduce a purification perturbation platform, named IMPRESS, to evaluate the effectiveness of imperceptible perturbations as a protective measure.
  arXiv  Detail & Related papers  (2023-10-30T03:33:41Z)
• DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models [79.71665540122498]
  We propose a method for detecting unauthorized data usage by planting the injected content into the protected dataset. Specifically, we modify the protected images by adding unique contents on these images using stealthy image warping functions. By analyzing whether the model has memorized the injected content, we can detect models that had illegally utilized the unauthorized data.
  arXiv  Detail & Related papers  (2023-07-06T16:27:39Z)

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.