DTVI: Dual-Stage Textual and Visual Intervention for Safe Text-to-Image Generation

• URL: http://arxiv.org/abs/2603.22041v2
• Date: Sun, 29 Mar 2026 04:28:10 GMT
• Title: DTVI: Dual-Stage Textual and Visual Intervention for Safe Text-to-Image Generation
• Abstract summary: Text-to-Image (T2I) diffusion models have demonstrated strong generation ability, but their potential to generate unsafe content raises significant safety concerns.<n>We propose DTVI, a dual-stage inference-time defense framework for safe T2I generation.
• Score: 10.071877020102557
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-Image (T2I) diffusion models have demonstrated strong generation ability, but their potential to generate unsafe content raises significant safety concerns. Existing inference-time defense methods typically perform category-agnostic token-level intervention in the text embedding space, which fails to capture malicious semantics distributed across the full token sequence and remains vulnerable to adversarial prompts. In this paper, we propose DTVI, a dual-stage inference-time defense framework for safe T2I generation. Unlike existing methods that intervene on specific token embeddings, our method introduces category-aware sequence-level intervention on the full prompt embedding to better capture distributed malicious semantics, and further attenuates the remaining unsafe influences during the visual generation stage. Experimental results on real-world unsafe prompts, adversarial prompts, and multiple harmful categories show that our method achieves effective and robust defense while preserving reasonable generation quality on benign prompts, obtaining an average Defense Success Rate (DSR) of 94.43% across sexual-category benchmarks and 88.56 across seven unsafe categories, while maintaining generation quality on benign prompts.

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)
• TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks [3.3681515336200403]
  We propose a training-free, inference-time defense framework that reformulates T2V safety as a causal intervention in a temporally structured semantic space.<n>TrajShield handles explicit unsafe prompts, jailbreak attacks, and temporally emergent risks in a unified manner.
  arXiv  Detail & Related papers  (2026-05-03T07:49:51Z)
• When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance [79.1968671824977]
  Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images.<n>We propose Conflict-aware Adaptive Safety Guidance (CASG), a training-free framework that dynamically identifies and applies the category-aligned safety direction during generation.<n>Experiments on T2I safety benchmarks demonstrate CASG's state-of-the-art performance, reducing the harmful rate by up to 15.4% compared to existing methods.
  arXiv  Detail & Related papers  (2026-02-24T13:20:31Z)
• 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)
• SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models [74.11062256255387]
  Text-to-image models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce harmful content.<n>We introduce SafeGuider, a two-step framework designed for robust safety control without compromising generation quality.<n>SafeGuider demonstrates exceptional effectiveness in minimizing attack success rates, achieving a maximum rate of only 5.48% across various attack scenarios.
  arXiv  Detail & Related papers  (2025-10-05T10:24:48Z)
• PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation [30.2092299298228]
  Text-to-image (T2I) models are vulnerable to producing not-safe-for-work (NSFW) content, such as violent or explicit imagery.<n>We propose PromptSafe, a gated prompt tuning framework that combines a lightweight, text-only supervised soft embedding with an inference-time gated control network.<n>We show that PromptSafe achieves a SOTA unsafe generation rate (2.36%) while preserving high benign fidelity.
  arXiv  Detail & Related papers  (2025-08-02T09:09:40Z)
• OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models [91.55634905861827]
  Over-refusal is a phenomenon known as $textitover-refusal$ that reduces the practical utility of T2I models.<n>We present OVERT ($textbfOVE$r-$textbfR$efusal evaluation on $textbfT$ext-to-image models), the first large-scale benchmark for assessing over-refusal behaviors.
  arXiv  Detail & Related papers  (2025-05-27T15:42:46Z)
• T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks [67.91652526657599]
  We formalize the T2V jailbreak attack as a discrete optimization problem and propose a joint objective-based optimization framework, called T2V-OptJail.<n>We conduct large-scale experiments on several T2V models, covering both open-source models and real commercial closed-source models.<n>The proposed method improves 11.4% and 10.0% over the existing state-of-the-art method in terms of attack success rate.
  arXiv  Detail & Related papers  (2025-05-10T16:04:52Z)
• Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding [16.188657772178747]
  We propose Embedding Sanitizer (ES), which enhances the safety of text-to-image models by sanitizing inappropriate concepts in prompt embeddings.<n>ES is the first interpretable safe generation framework that assigns a score to each token in the prompt to indicate its potential harmfulness.
  arXiv  Detail & Related papers  (2024-11-15T16:29:02Z)
• ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time [12.160713548659457]
  adversarial visual inputs can easily bypass VLM defense mechanisms.<n>We propose a novel two-phase inference-time alignment framework, evaluating input visual contents and output responses.<n>Experiments show that ETA outperforms baseline methods in terms of harmlessness, helpfulness, and efficiency.
  arXiv  Detail & Related papers  (2024-10-09T07:21:43Z)

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.