Precise Shield: Explaining and Aligning VLLM Safety via Neuron-Level Guidance

• URL: http://arxiv.org/abs/2604.08881v1
• Date: Fri, 10 Apr 2026 02:42:52 GMT
• Title: Precise Shield: Explaining and Aligning VLLM Safety via Neuron-Level Guidance
• Abstract summary: In real-world deployments, Vision-Language Large Models (VLLMs) face critical challenges from multilingual and multimodal composite attacks.<n>We propose Precise Shield, a two-stage framework that first identifies safety neurons by contrasting activation patterns between harmful and benign inputs.<n>This strategy substantially improves safety while preserving multilingual and multimodal generalization.
• Score: 64.18179414483966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In real-world deployments, Vision-Language Large Models (VLLMs) face critical challenges from multilingual and multimodal composite attacks: harmful images paired with low-resource language texts can easily bypass defenses designed for high-resource language scenarios, exposing structural blind spots in current cross-lingual and cross-modal safety methods. This raises a mechanistic question: where is safety capability instantiated within the model, and how is it distributed across languages and modalities? Prior studies on pure-text LLMs have identified cross-lingual shared safety neurons, suggesting that safety may be governed by a small subset of critical neurons. Leveraging this insight, we propose Precise Shield, a two-stage framework that first identifies safety neurons by contrasting activation patterns between harmful and benign inputs, and then constrains parameter updates strictly within this subspace via gradient masking with affecting fewer than 0.03% of parameters. This strategy substantially improves safety while preserving multilingual and multimodal generalization. Further analysis reveals a moderate overlap of safety neurons across languages and modalities, enabling zero-shot cross-lingual and cross-modal transfer of safety capabilities, and offering a new direction for neuron-level, transfer-based safety enhancement.

Related papers

• Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways [44.23839982612062]
  We identify and target the cross-layer functional pathways formed during safety signal propagation.<n>We propose a pathways-targeted alignment method based on the cross-lingual shared safety pathways.<n> Experimental results show that updating only a small fraction of pathway parameters significantly improves safety in NHR languages.
  arXiv  Detail & Related papers  (2026-08-10T03:48:47Z)
• No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks [61.07406641465909]
  We propose distributed safety alignment, which encodes safety capabilities across multiple computational neurons.<n>We show that DSA substantially improves against white-box neuron-level safety attacks while preserving the model's general language and multimodal utility.
  arXiv  Detail & Related papers  (2026-08-02T17:49:07Z)
• SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs [69.51621286001262]
  We introduce SafeNexus, a cross-modal safety alignment framework that adopts a dedicated neuron-level intervention strategy.<n>We identify modality-bound safety neurons (BS-Neurons), and validate their role in regulating safety behavior within each modality.<n>We propose two safety alignment strategies: activation-level safety amplifier and safety neuron calibrator.
  arXiv  Detail & Related papers  (2026-07-31T02:45:56Z)
• One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs [63.29484454957031]
  We propose a neuron-level cross-dimensional safety alignment framework driven by modality- and language-shared safety neurons (MLS-Neurons)<n>Our method significantly outperforms state-of-the-art approaches across diverse multilingual and multimodal safety benchmarks.
  arXiv  Detail & Related papers  (2026-07-30T09:30:03Z)
• Multilingual Safety Alignment via Self-Distillation [17.94152626632751]
  Large language models (LLMs) exhibit severe multilingual safety misalignment.<n>We propose a cross-lingual safeguard transfer framework named Multilingual Self-Distillation (MSD)<n>Our framework is flexible and can be integrated with different self-distillation strategies.
  arXiv  Detail & Related papers  (2026-05-03T14:22:49Z)
• LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety [88.98698230989186]
  Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities in low-resource languages.<n>We attribute this gap to a mismatch between language-agnostic semantic understanding ability and language-dominant safety alignment biased toward high-resource languages.<n>We propose Language-Agnostic Semantic Alignment (LASA), which anchors safety alignment directly in semantic bottlenecks.
  arXiv  Detail & Related papers  (2026-04-13T15:59:50Z)
• Multilingual Safety Alignment Via Sparse Weight Editing [11.684928396991742]
  We propose a training-free alignment framework based on Sparse Weight Editing.<n>We derive a closed-form solution to optimally map the harmful representations of LRLs to the robust safety subspaces of HRLs.<n>Our method substantially reduces Attack Success Rate (ASR) in LRLs with negligible impact on general reasoning capabilities.
  arXiv  Detail & Related papers  (2026-02-26T02:46:13Z)
• Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons [49.772147495578736]
  Cross-lingual shared safety neurons (SS-Neurons) regulate safety behavior across languages.<n>We propose a neuron-oriented training strategy that targets SS-Neurons based on language resource distribution and model architecture.
  arXiv  Detail & Related papers  (2026-02-01T15:28:02Z)
• Fine-Grained Safety Neurons with Training-Free Continual Projection to Reduce LLM Fine Tuning Risks [22.059668583508365]
  We propose the Fine-Grained Safety Neurons (FGSN) with Training-Free Continual Projection method to reduce the fine-tuning safety risks.<n>FGSN inherently integrates the multi-scale interactions between safety layers and neurons, localizing sparser and more precise fine-grained safety neurons.
  arXiv  Detail & Related papers  (2025-08-08T03:20:25Z)
• Automating Steering for Safe Multimodal Large Language Models [58.36932318051907]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)
• Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models [83.80177564873094]
  We propose a unified multimodal universal jailbreak attack framework.<n>We evaluate the undesirable context generation of MLLMs like LLaVA, Yi-VL, MiniGPT4, MiniGPT-v2, and InstructBLIP.<n>This study underscores the urgent need for robust safety measures in MLLMs.
  arXiv  Detail & Related papers  (2025-06-02T04:33:56Z)
• MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety [56.77103365251923]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking.<n>This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is often limited.<n>We introduce a multilingual guardrail with reasoning for prompt classification.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)

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.