Related papers: SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models

SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models

URL: http://arxiv.org/abs/2609.03544v1
Date: Thu, 03 Sep 2026 08:43:07 GMT
Title: SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models
Abstract summary: 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.
Score: 46.33456413143737
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Existing safety alignment methods for vision-language models usually modify the model behavior globally: once the safety parameters are trained or loaded, they participate in both unsafe and already-safe generations. This always-on intervention can unnecessarily perturb the model's original reasoning path and degrade general multimodal capabilities. We argue that safety alignment should be an on-demand intervention rather than a permanent modification to every decoding trajectory. To this end, we propose a streaming recognition and gated LoRA framework for intrinsic VLM safety. During autoregressive generation, a lightweight recognizer estimates whether the current pre-token generation state is safe or unsafe. Its output updates the LoRA gate for the following decoding step; otherwise, generation follows the frozen-backbone policy. The 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. Experiments across multiple safety and general-purpose benchmarks demonstrate the effectiveness of our method in post-alignment settings.

Related papers

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs [13.624659633750861]
Existing safety mechanisms for large language models (MLLMs) face a fundamental trade-off between safety and utility.<n>We propose a paradigm shift toward output-aware safety guardrails.<n>Our method operates within the model's hidden state space to predict whether the forthcoming generation will be unsafe.
arXiv Detail & Related papers (2026-06-20T12:09:13Z)
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)
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)
RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
arXiv Detail & Related papers (2025-12-24T15:01:26Z)
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)
Safe Vision-Language Models via Unsafe Weights Manipulation [75.04426753720551]
We revise safety evaluation by introducing Safe-Ground, a new set of metrics that evaluate safety at different levels of granularity.<n>We take a different direction and explore whether it is possible to make a model safer without training, introducing Unsafe Weights Manipulation (UWM)<n>UWM uses a calibration set of safe and unsafe instances to compare activations between safe and unsafe content, identifying the most important parameters for processing the latter.
arXiv Detail & Related papers (2025-03-14T17:00:22Z)
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models [30.93821289892195]
We propose IRR (Identify, Remove, and Recalibrate for Safety Realignment) that performs safety realignment for LLMs.<n>The core of IRR is to identify and remove unsafe delta parameters from the fine-tuned models, while recalibrating the retained ones.<n>Our results demonstrate that IRR significantly enhances the safety performance of fine-tuned models on safety benchmarks, such as harmful queries and jailbreak attacks.
arXiv Detail & Related papers (2024-12-15T03:58:38Z)
A safety realignment framework via subspace-oriented model fusion for large language models [22.588716190505963]
We introduce a safety realignment framework through subspace-oriented model fusion (SOMF) Our approach begins by disentangling all task vectors from the weights of each fine-tuned model. We then identify safety-related regions within these vectors by subspace masking techniques.
arXiv Detail & Related papers (2024-05-15T03:04:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.