Imagen de Portada

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Yifan, Guo, Hangyu, Zhou, Kun, Zhao, Wayne Xin, Wen, Ji-Rong
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning
por: Du, Yifan, et al.
Publicado: (2023)

[WIP] Jailbreak Paradox: The Achilles' Heel of LLMs
por: Rao, Abhinav, et al.
Publicado: (2024)

Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models
por: Liu, Zikang, et al.
Publicado: (2025)

Analyzing and Mitigating Object Hallucination: A Training Bias Perspective
por: Li, Yifan, et al.
Publicado: (2025)

Less is More: High-value Data Selection for Visual Instruction Tuning
por: Liu, Zikang, et al.
Publicado: (2024)

Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment
por: Chen, Zhipeng, et al.
Publicado: (2024)

Exploring the Design Space of Visual Context Representation in Video MLLMs
por: Du, Yifan, et al.
Publicado: (2024)

Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models
por: Yang, Hao, et al.
Publicado: (2024)

Towards Event-oriented Long Video Understanding
por: Du, Yifan, et al.
Publicado: (2024)

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

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
por: Liu, Jianyu, et al.
Publicado: (2025)

Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models
por: Chen, Yiming, et al.
Publicado: (2024)

Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
por: Guo, Geyang, et al.
Publicado: (2023)

Against The Achilles' Heel: A Survey on Red Teaming for Generative Models
por: Lin, Lizhi, et al.
Publicado: (2024)

Unleashing Perception-Time Scaling to Multimodal Reasoning Models
por: Li, Yifan, et al.
Publicado: (2025)

Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
por: Liang, Yupu, et al.
Publicado: (2025)

Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
por: Xiao, Xin, et al.
Publicado: (2024)

Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models
por: Nihal, Ragib Amin, et al.
Publicado: (2025)

ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
por: Cheng, Xiaoxue, et al.
Publicado: (2024)

Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
por: Wang, Songping, et al.
Publicado: (2026)

Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models
por: Chen, Zhipeng, et al.
Publicado: (2024)

Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models
por: Zhou, Qiji, et al.
Publicado: (2024)

Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models
por: Wang, Wenxuan, et al.
Publicado: (2024)

GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation
por: Cai, Shihao, et al.
Publicado: (2024)

E$^2$AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Models
por: Lu, Liming, et al.
Publicado: (2025)

Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint
por: Chen, Zhipeng, et al.
Publicado: (2024)

From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models
por: Jin, Haibo, et al.
Publicado: (2025)

Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings
por: Huang, Yue, et al.
Publicado: (2024)

Jailbreaking Multimodal Large Language Models using Multi-Clip Video
por: Kang, Choongwon, et al.
Publicado: (2026)

On Domain-Adaptive Post-Training for Multimodal Large Language Models
por: Cheng, Daixuan, et al.
Publicado: (2024)

LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
por: You, Zebin, et al.
Publicado: (2025)

Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment
por: Li, Yunxin, et al.
Publicado: (2024)

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph
por: Jiang, Jinhao, et al.
Publicado: (2023)

The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning
por: Zhang, Xudong, et al.
Publicado: (2026)

Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models
por: Sun, Haoxiang, et al.
Publicado: (2025)

Ovis: Structural Embedding Alignment for Multimodal Large Language Model
por: Lu, Shiyin, et al.
Publicado: (2024)

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

BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models
por: Dong, Zican, et al.
Publicado: (2023)

UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
por: Ji, Yifan, et al.
Publicado: (2026)

MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment
por: Liu, Jihao, et al.
Publicado: (2024)