Cover Image

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Siyin, Ye, Xingsong, Cheng, Qinyuan, Duan, Junwen, Li, Shimin, Fu, Jinlan, Qiu, Xipeng, Huang, Xuanjing
Format:	Preprint
Published:	2024
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LLM can Achieve Self-Regulation via Hyperparameter Aware Generation
by: Wang, Siyin, et al.
Published: (2024)

Agent Alignment in Evolving Social Norms
by: Li, Shimin, et al.
Published: (2024)

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning
by: Wang, Siyin, et al.
Published: (2025)

Scaling Laws for Fact Memorization of Large Language Models
by: Lu, Xingyu, et al.
Published: (2024)

World-aware Planning Narratives Enhance Large Vision-Language Model Planner
by: Shi, Junhao, et al.
Published: (2025)

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
by: Fu, Jinlan, et al.
Published: (2025)

Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models
by: Cai, Wei, et al.
Published: (2025)

In-Memory Learning: A Declarative Learning Framework for Large Language Models
by: Wang, Bo, et al.
Published: (2024)

InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
by: Huang, Kexin, et al.
Published: (2025)

Dynamic and Generalizable Process Reward Modeling
by: Yin, Zhangyue, et al.
Published: (2025)

CodecBench: A Comprehensive Benchmark for Acoustic and Semantic Evaluation
by: Deng, Ruifan, et al.
Published: (2025)

Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
by: Zeng, Zhiyuan, et al.
Published: (2024)

Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models
by: Liu, Peiju, et al.
Published: (2026)

AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models
by: Zhu, Qin, et al.
Published: (2025)

Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models
by: Xu, Ningyu, et al.
Published: (2026)

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
by: Zhang, Yongting, et al.
Published: (2024)

LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
by: Fei, Senyu, et al.
Published: (2025)

VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
by: Wang, Yikun, et al.
Published: (2025)

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
by: Cui, Chenhang, et al.
Published: (2024)

ClawSafety: "Safe" LLMs, Unsafe Agents
by: Wei, Bowen, et al.
Published: (2026)

Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation
by: Zhu, Qin, et al.
Published: (2024)

Safe Vision-Language Models via Unsafe Weights Manipulation
by: D'Incà, Moreno, et al.
Published: (2025)

SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
by: Zhang, Xin, et al.
Published: (2023)

Unsafe Impedance: Safe Languages and Safe by Design Software
by: Barney, Lee, et al.
Published: (2024)

Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework
by: Sun, Yuhong, et al.
Published: (2025)

RoboOmni: Proactive Robot Manipulation in Omni-modal Context
by: Wang, Siyin, et al.
Published: (2025)

Computed Tomography Visual Question Answering with Cross-modal Feature Graphing
by: Tian, Yuanhe, et al.
Published: (2025)

World Action Models: The Next Frontier in Embodied AI
by: Wang, Siyin, et al.
Published: (2026)

Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge
by: Fu, Jinlan, et al.
Published: (2024)

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
by: Zhang, Haowei, et al.
Published: (2026)

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
by: Chen, Qian, et al.
Published: (2026)

MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation
by: Fu, Jinlan, et al.
Published: (2025)

Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
by: Hashemzadeh, Maryam, et al.
Published: (2026)

ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
by: Zhu, Changtai, et al.
Published: (2025)

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
by: Zeng, Zhiyuan, et al.
Published: (2025)

SafeLink: Safety-Critical Control Under Dynamic and Irregular Unsafe Regions
by: Hu, Songqiao, et al.
Published: (2025)

XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs
by: Gong, Yitian, et al.
Published: (2025)

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
by: Li, Tianhao, et al.
Published: (2024)

SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
by: Fei, Senyu, et al.
Published: (2025)

Multi-hop Reasoning via Early Knowledge Alignment
by: Wang, Yuxin, et al.
Published: (2025)