arXiv Machine Learning
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
Sep 21
MME-Safety: A Fine-grained Benchmark for Safety Evaluation of MLLMs
arXiv:2609.20850v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easi...
arXiv Computer Vision
Sep 16
Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models
The paper examines how the tight integration of multimodal understanding and image generation in Unified Multimodal Models (UMMs) can create new safety vulnerabilities. It introduces RICE, an attack framework that exploits bidirectional interactions between generation and understanding to propagate unsafe signals across modalities. Experiments demonstrate high attack success rates in both Generation‑to‑Understanding and Understanding‑to‑Generation pathways, revealing previously overlooked safety weaknesses in UMMs.
arXiv AI
Aug 19
COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models
The paper introduces COMIC, a reference‑aware safety gate designed for multimodal large language models (MLLMs). COMIC detects the operation requested by a user, identifies visual targets through OCR and open‑vocabulary proposals, and evaluates safety on explicit operation‑target pairs, using max‑risk aggregation and quality‑aware routing to decide whether to allow or block a request. Experiments on several open‑source MLLMs and jailbreak benchmarks show that COMIC improves robustness while maintaining benign utility and efficiency.
arXiv Computer Vision
Oct 12
A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
The paper introduces Multi-Modal Typography, a systematic investigation into how perturbations applied to speech and on-screen text can compromise audio‑visual reasoning in large language models. Experiments on the WorldSense benchmark show that such attacks can raise the attack success rate against Gemini 3.7 Flash from 9.53% to 43.41%, and fine‑tuning can reduce the success rate for Qwen2.5‑Omni‑7B from 60.6% to 52.0%. The study highlights that cross‑modal typography attacks are a significant, yet underexplored, vulnerability in multi‑modal reasoning systems.
arXiv AI
Aug 28
Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation
Multi2AV‑Safety is a new benchmark for evaluating safety in multimodal-to-audio‑video generation. It covers all 11 non‑singleton conditioning configurations (text, image, audio, video) and contains 11,024 attack instances. The benchmark reveals that safety guards often fail when harmful semantics arise from combinations of benign inputs or when explicit harmful cues are masked by benign multimodal context, highlighting a gap in compositional risk perception.
arXiv AI
Jun 6
MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models
arXiv:2606. 05177v1 Announce Type: cross Abstract: Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text.