Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation

• URL: http://arxiv.org/abs/2606.05290v1
• Date: Wed, 03 Jun 2026 18:00:04 GMT
• Title: Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation
• Abstract summary: 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.
• Score: 52.122731171289665
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture. In this work, we ask whether safety can be represented as a portable latent direction, learned once and reused across heterogeneous generators. We introduce the first framework for cross-model safety steering, in which a safety direction is estimated in a source LLM from paired safe-unsafe prompts, transported to a target generator through a lightweight alignment fitted on benign data alone, and applied at inference time. Crucially, our pipeline never accesses unsafe data on the target side, isolating whether safety can be transferred through shared representation geometry. Beyond a single global direction, we also identify a multi-vector extension that captures category-specific safety behaviors, enabling more selective control. We evaluate our approach in text-to-image and text-to-video generation across diverse source-target model pairs. Across models, transferred safety directions achieve ASR reduction and CLIP-Score/FID trade-offs comparable to directions learned natively on the target model using unsafe data, while requiring no target-side unsafe data. This indicates that safety improvements do not come at the expense of generation quality. Our results point to a modular view of safety: safety-relevant behavior is not purely model-local, but can be controlled through latent directions that persist across models. This suggests a new path toward lightweight, reusable safety mechanisms that do not require target-side unsafe data.

Related papers

• SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models [46.33456413143737]
  We propose a streaming recognition and gated LoRA framework for intrinsic VLM safety.<n>LoRA module is trained from unsafe prefixes, transition statements, and safe continuations, so that it learns to redirect unsafe generations back to safe responses after activation.
  arXiv  Detail & Related papers  (2026-09-03T08:43:07Z)
• Safe Vision Language Action Models via Barrier Enhanced Flow Matching [0.0]
  This article presents a modular inference framework that integrates Flow Matching generative models with formal Control Barrier Function safety guarantees.<n>By employing a smooth Log-Sum-Exponential aggregate barrier, we enforce safety over entire action chunks.<n>We validate the approach on two robotic manipulation platforms and a 2D navigation benchmark, verifying that our framework achieves reliable safety without degrading the success rate of the model.
  arXiv  Detail & Related papers  (2026-07-31T15:56:19Z)
• SafeGene: Reusable Adapters for Transferable Safety Alignment [31.247158830484604]
  We propose SafeGene, a reusable safety-adapter module for cross-task reuse.<n>We show that SafeGene-enhanced models reduce harmful response rates while maintaining downstream performance.
  arXiv  Detail & Related papers  (2026-06-02T14:51:14Z)
• Selective Safety Steering via Value-Filtered Decoding [54.87935112120107]
  Large language models (LLMs) are trained to align with human values, but their generations may still violate safety constraints.<n>Existing decoding-time steering methods often intervene unnecessarily, modifying generations that would have been safe under the base model.<n>We propose a new test-time steering method designed to reduce such unnecessary interventions while improving the safety of unsafe responses.
  arXiv  Detail & Related papers  (2026-05-14T12:13:08Z)
• SecureBreak -- A dataset towards safe and secure models [3.797867929356259]
  This paper introduces SecureBreak, a safety-oriented dataset designed to support the development of AI-driven solutions for detecting harmful LLM outputs.<n>The dataset is highly reliable due to careful manual annotation, where labels are assigned conservatively to ensure safety.<n>Tests with pre-trained LLMs show improved results after fine-tuning on SecureBreak.
  arXiv  Detail & Related papers  (2026-03-23T13:41:05Z)
• Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment [41.47485992177247]
  We propose Safe Transformer, a modular approach that augments pre-trained language models.<n>The safety bit serves as both an interpretable signal of the model's safety classification and a controllable switch.<n>In red-team benchmarks, Safe Transformer achieves near-zero Attack Success Rate.
  arXiv  Detail & Related papers  (2026-03-06T02:54:16Z)
• Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation [2.5489046505746704]
  In this paper, we introduce a unified probabilistic framework using a Maximum Mean Discrepancy (MMD) potential for image generation tasks.<n>We leverage control-barrier functions analysis to justify the existence of a critical time window in which negative guidance must be strong.<n>We evaluate our unified framework on several realistic safe generation scenarios, confirming that negative guidance should be applied in the early stages of the denoising process.
  arXiv  Detail & Related papers  (2026-03-02T07:31:29Z)
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• Shape it Up! Restoring LLM Safety during Finetuning [65.75757313781104]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• What Makes and Breaks Safety Fine-tuning? A Mechanistic Study [64.9691741899956]
  Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. We design a synthetic data generation framework that captures salient aspects of an unsafe input. Using this, we investigate three well-known safety fine-tuning methods.
  arXiv  Detail & Related papers  (2024-07-14T16:12:57Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position.<n>DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)

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.