VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety
- URL: http://arxiv.org/abs/2510.18214v1
- Date: Tue, 21 Oct 2025 01:30:31 GMT
- Title: VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety
- Authors: Shruti Palaskar, Leon Gatys, Mona Abdelrahman, Mar Jacobo, Larry Lindsey, Rutika Moharir, Gunnar Lund, Yang Xu, Navid Shiee, Jeffrey Bigham, Charles Maalouf, Joseph Yitan Cheng,
- Abstract summary: We present Vision Language Safety Understanding, a comprehensive framework to evaluate multimodal safety.<n>Our evaluation of eleven state-of-the-art models reveals systematic joint understanding failures.<n>Our framework exposes weaknesses in joint image-text understanding and alignment gaps in current models.
- Score: 3.1109025622085693
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish clearly unsafe content from borderline cases, leading to problematic over-blocking or under-refusal of genuinely harmful content. We present Vision Language Safety Understanding (VLSU), a comprehensive framework to systematically evaluate multimodal safety through fine-grained severity classification and combinatorial analysis across 17 distinct safety patterns. Using a multi-stage pipeline with real-world images and human annotation, we construct a large-scale benchmark of 8,187 samples spanning 15 harm categories. Our evaluation of eleven state-of-the-art models reveals systematic joint understanding failures: while models achieve 90%-plus accuracy on clear unimodal safety signals, performance degrades substantially to 20-55% when joint image-text reasoning is required to determine the safety label. Most critically, 34% of errors in joint image-text safety classification occur despite correct classification of the individual modalities, further demonstrating absent compositional reasoning capabilities. Additionally, we find that models struggle to balance refusing unsafe content while still responding to borderline cases that deserve engagement. For example, we find that instruction framing can reduce the over-blocking rate on borderline content from 62.4% to 10.4% in Gemini-1.5, but only at the cost of under-refusing on unsafe content with refusal rate dropping from 90.8% to 53.9%. Overall, our framework exposes weaknesses in joint image-text understanding and alignment gaps in current models, and provides a critical test bed to enable the next milestones in research on robust vision-language safety.
Related papers
- Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context [82.32380418146656]
Health-ORSC-Bench is the first large-scale benchmark designed to measure textbfOver-Refusal and textbfSafe Completion quality in healthcare.<n>Our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity.<n>Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants.
arXiv Detail & Related papers (2026-01-25T01:28:52Z) - AI Transparency Atlas: Framework, Scoring, and Real-Time Model Card Evaluation Pipeline [2.1787849426740364]
We analyzed documentation from five frontier models (Gemini 3, Grok 4.1, Llama 4, GPT-5, and Claude 4.5) and 100 Hugging Face model cards.<n>We developed a weighted transparency framework with 8 sections and 23 subsections that prioritizes safety-critical disclosures.
arXiv Detail & Related papers (2025-12-13T19:48:44Z) - OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models [54.80460603255789]
We introduce OutSafe-Bench, the first most comprehensive content safety evaluation test suite designed for the multimodal era.<n>OutSafe-Bench includes a large-scale dataset that spans four modalities, featuring over 18,000 bilingual (Chinese and English) text prompts, 4,500 images, 450 audio clips and 450 videos, all systematically annotated across nine critical content risk categories.<n>In addition to the dataset, we introduce a Multidimensional Cross Risk Score (MCRS), a novel metric designed to model and assess overlapping and correlated content risks across different categories.
arXiv Detail & Related papers (2025-11-13T13:18:27Z) - DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models [59.45605332033458]
Safety mechanisms can backfire, causing over-refusal, where models decline benign requests out of excessive caution.<n>No existing benchmark has systematically addressed over-refusal in the visual modality.<n>This setting introduces unique challenges, such as dual-use cases where an instruction is harmless, but the accompanying image contains harmful content.
arXiv Detail & Related papers (2025-10-12T23:21:34Z) - Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition [12.054081112688074]
Vision-Language Models (VLMs) have shown capabilities in interpreting visual content, but their reliability in safety-critical scenarios remains insufficiently explored.<n>We introduce VERI, a diagnostic benchmark comprising 200 synthetic images (100 contrastive pairs) and an additional 50 real-world images (25 pairs) for validation.<n>Each emergency scene is paired with a visually similar but safe counterpart through human verification.
arXiv Detail & Related papers (2025-05-21T10:57:40Z) - FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning [12.467239356591238]
FalseReject is a comprehensive resource containing 16k seemingly toxic queries accompanied by structured responses across 44 safety-related categories.<n>We propose a graph-informed adversarial multi-agent interaction framework to generate diverse and complex prompts.<n>We show that supervised finetuning with FalseReject substantially reduces unnecessary refusals without compromising overall safety or general language capabilities.
arXiv Detail & Related papers (2025-05-12T20:45:25Z) - Advancing Neural Network Verification through Hierarchical Safety Abstract Interpretation [52.626086874715284]
We introduce a novel problem formulation called Abstract DNN-Verification, which verifies a hierarchical structure of unsafe outputs.<n>By leveraging abstract interpretation and reasoning about output reachable sets, our approach enables assessing multiple safety levels during the formal verification process.<n>Our contributions include a theoretical exploration of the relationship between our novel abstract safety formulation and existing approaches.
arXiv Detail & Related papers (2025-05-08T13:29:46Z) - Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs [56.440345471966666]
Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images.<n>This paper introduces MMSafeAware, the first comprehensive multimodal safety awareness benchmark designed to evaluate MLLMs across 29 safety scenarios.<n> MMSafeAware includes both unsafe and over-safety subsets to assess models abilities to correctly identify unsafe content and avoid over-sensitivity that can hinder helpfulness.
arXiv Detail & Related papers (2025-02-16T16:12:40Z) - SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior [56.10557932893919]
We present SafetyAnalyst, a novel AI safety moderation framework.<n>Given an AI behavior, SafetyAnalyst uses chain-of-thought reasoning to analyze its potential consequences.<n>It aggregates effects into a harmfulness score using 28 fully interpretable weight parameters.
arXiv Detail & Related papers (2024-10-22T03:38:37Z)
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.