Cover Image

MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Xirui, Zhou, Hengguang, Wang, Ruochen, Zhou, Tianyi, Cheng, Minhao, Hsieh, Cho-Jui
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
by: Li, Xirui, et al.
Published: (2024)

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
by: Zhou, Hengguang, et al.
Published: (2025)

MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion
by: Li, Sen, et al.
Published: (2024)

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
by: Lee, DongGeon, et al.
Published: (2025)

Text is All You Need for Vision-Language Model Jailbreaking
by: Chen, Yihang, et al.
Published: (2026)

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector
by: Huang, Youcheng, et al.
Published: (2024)

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
by: Rong, Xuankun, et al.
Published: (2025)

Jailbreaking Attack against Multimodal Large Language Model
by: Niu, Zhenxing, et al.
Published: (2024)

Image-Based Geolocation Using Large Vision-Language Models
by: Liu, Yi, et al.
Published: (2024)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
by: Ding, Yi, et al.
Published: (2025)

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images
by: Naseh, Ali, et al.
Published: (2024)

Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenarios
by: Qu, Jingen, et al.
Published: (2025)

Invisible Backdoor Attacks on Diffusion Models
by: Li, Sen, et al.
Published: (2024)

Few-Shot Adversarial Prompt Learning on Vision-Language Models
by: Zhou, Yiwei, et al.
Published: (2024)

Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
by: Xiong, Yuan, et al.
Published: (2025)

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
by: Jin, Haibo, et al.
Published: (2024)

Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory
by: Zhang, Ce, et al.
Published: (2026)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
by: Kim, Hee-Seon, et al.
Published: (2024)

SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
by: Li, Xinfeng, et al.
Published: (2024)

Rethinking Machine Unlearning in Image Generation Models
by: Liu, Renyang, et al.
Published: (2025)

Understanding the Impact of Negative Prompts: When and How Do They Take Effect?
by: Ban, Yuanhao, et al.
Published: (2024)

Test-Time Backdoor Attacks on Multimodal Large Language Models
by: Lu, Dong, et al.
Published: (2024)

SafeText: Safe Text-to-image Models via Aligning the Text Encoder
by: Hu, Yuepeng, et al.
Published: (2025)

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
by: Chen, Beitao, et al.
Published: (2025)

OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
by: Jia, Xiaojun, et al.
Published: (2025)

FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution
by: Zhou, Qi, et al.
Published: (2024)

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
by: Jiang, Zhengyuan, et al.
Published: (2025)

JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
by: Jin, Haibo, et al.
Published: (2024)

Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model
by: Meng, Jiayang, et al.
Published: (2024)

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
by: Yin, Ziyi, et al.
Published: (2023)

VLSBench: Unveiling Visual Leakage in Multimodal Safety
by: Hu, Xuhao, et al.
Published: (2024)

Dissecting Adversarial Robustness of Multimodal LM Agents
by: Wu, Chen Henry, et al.
Published: (2024)

Benchmarking Large Multimodal Models against Common Corruptions
by: Zhang, Jiawei, et al.
Published: (2024)

The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise
by: Ban, Yuanhao, et al.
Published: (2024)

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
by: Liao, Qilin, et al.
Published: (2025)

Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security
by: Fan, Yihe, et al.
Published: (2024)

VLMs Can Aggregate Scattered Training Patches
by: Zhou, Zhanhui, et al.
Published: (2025)

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
by: Yang, Wenkui, et al.
Published: (2026)

IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding
by: Li, Junxian, et al.
Published: (2025)

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
by: Pi, Renjie, et al.
Published: (2024)