Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models

• URL: http://arxiv.org/abs/2604.02265v1
• Date: Thu, 02 Apr 2026 16:59:28 GMT
• Title: Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models
• Abstract summary: We propose an inference-time steering framework that leverages gradient feedback from frozen pretrained foundation models to guide the generation process without modifying the underlying generator.<n>Our framework provides a principled approach for utilizing foundation models as semantic energy estimators, enabling reliable and scalable safety control for text-to-image generation.
• Score: 19.89268359258615
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit scalability. We propose an inference-time steering framework that leverages gradient feedback from frozen pretrained foundation models to guide the generation process without modifying the underlying generator. Our key observation is that vision-language foundation models encode rich semantic representations that can be repurposed as off-the-shelf supervisory signals during generation. By injecting such feedback through clean latent estimates at each sampling step, our method formulates safety steering as an energy-based sampling problem. This design enables modular, training-free safety control that is compatible with both diffusion and flow-matching models and can generalize across diverse visual concepts. Experiments demonstrate state-of-the-art robustness against NSFW red-teaming benchmarks and effective multi-target steering, while preserving high generation quality on benign non-targeted prompts. Our framework provides a principled approach for utilizing foundation models as semantic energy estimators, enabling reliable and scalable safety control for text-to-image generation.

Related papers

• Introspective Attention Modulation for Safe Text-to-Image Generation [37.67434449197168]
  State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content.<n>We introduce a unique approach that achieves safety by regulating the model's attention dynamics through inference-time introspection.
  arXiv  Detail & Related papers  (2026-07-16T12:53:45Z)
• Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation [52.122731171289665]
  We introduce the first framework for cross-model safety steering.<n>Our pipeline never accesses unsafe data on the target side.<n>We evaluate our approach in text-to-image and text-to-video generation across diverse source-target model pairs.
  arXiv  Detail & Related papers  (2026-06-03T18:00:04Z)
• Provably Safe Generative Sampling with Constricting Barrier Functions [1.8377602530643375]
  Flow-based generative models have achieved remarkable success in learning complex data distributions.<n>We propose a safety filtering framework that acts as an online shield for any pre-trained generative model.<n>We prove that this mechanism guarantees safe sampling while minimizing the distributional shift from the original model at each sampling step.
  arXiv  Detail & Related papers  (2026-02-24T23:06:58Z)
• 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)
• CGCE: Classifier-Guided Concept Erasure in Generative Models [53.7410000675294]
  Concept erasure has been developed to remove undesirable concepts from pre-trained models.<n>Existing methods remain vulnerable to adversarial attacks that can regenerate the erased content.<n>We introduce an efficient plug-and-play framework that provides robust concept erasure for diverse generative models.
  arXiv  Detail & Related papers  (2025-11-08T05:38:18Z)
• ScaleWeaver: Weaving Efficient Controllable T2I Generation with Multi-Scale Reference Attention [86.93601565563954]
  ScaleWeaver is a framework designed to achieve high-fidelity, controllable generation upon advanced visual autoregressive( VAR) models.<n>The proposed Reference Attention module discards the unnecessary attention from image$rightarrow$condition, reducing computational cost.<n>Experiments show that ScaleWeaver delivers high-quality generation and precise control while attaining superior efficiency over diffusion-based methods.
  arXiv  Detail & Related papers  (2025-10-16T17:00:59Z)
• 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)
• 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)
• CAR: Controllable Autoregressive Modeling for Visual Generation [100.33455832783416]
  Controllable AutoRegressive Modeling (CAR) is a novel, plug-and-play framework that integrates conditional control into multi-scale latent variable modeling. CAR progressively refines and captures control representations, which are injected into each autoregressive step of the pre-trained model to guide the generation process. Our approach demonstrates excellent controllability across various types of conditions and delivers higher image quality compared to previous methods.
  arXiv  Detail & Related papers  (2024-10-07T00:55:42Z)
• SteerDiff: Steering towards Safe Text-to-Image Diffusion Models [6.112695628229525]
  Text-to-image (T2I) diffusion models can be misused to produce inappropriate content.<n>We introduce SteerDiff, a lightweight adaptor module designed to act as an intermediary between user input and the diffusion model.<n>We conduct extensive experiments across various concept unlearning tasks to evaluate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-10-03T17:34:55Z)

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.