Cover Image

Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jingru, Ren, Wei, Zhu, Tianqing
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models
by: Khan, Mohammed Safi Ur Rahman, et al.
Published: (2026)

Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
by: Li, Bin, et al.
Published: (2025)

Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
by: Fazli, Mehrdad, et al.
Published: (2025)

"See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models
by: Gu, Jihao, et al.
Published: (2025)

ColorFoil: Investigating Color Blindness in Large Vision and Language Models
by: Samin, Ahnaf Mozib, et al.
Published: (2024)

Instruction-Following Evaluation of Large Vision-Language Models
by: Shiono, Daiki, et al.
Published: (2025)

VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
by: Wang, Zihu, et al.
Published: (2025)

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
by: Zhang, Ce, et al.
Published: (2025)

ColorBlindnessEval: Can Vision-Language Models Pass Color Blindness Tests?
by: Ling, Zijian, et al.
Published: (2025)

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

Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
by: Xu, Shicheng, et al.
Published: (2024)

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models
by: Wang, Zhiqiang, et al.
Published: (2026)

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
by: Lee, Seongyun, et al.
Published: (2024)

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
by: Li, Yue, et al.
Published: (2025)

PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model
by: Arif, Kazi Hasan Ibn, et al.
Published: (2025)

IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models
by: You, Haoxuan, et al.
Published: (2023)

Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance
by: Zhao, Haozhe, et al.
Published: (2024)

DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes
by: Wang, Zhaowei, et al.
Published: (2024)

NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
by: Li, Baiqi, et al.
Published: (2024)

BLINK: Multimodal Large Language Models Can See but Not Perceive
by: Fu, Xingyu, et al.
Published: (2024)

Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models
by: Nazir, Maham, et al.
Published: (2026)

Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving
by: Li, Yue, et al.
Published: (2025)

Show and Guide: Instructional-Plan Grounded Vision and Language Model
by: Glória-Silva, Diogo, et al.
Published: (2024)

Investigating Spatial Attention Bias in Vision-Language Models
by: Chaudhary, Aryan, et al.
Published: (2025)

Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks
by: Jia, Mengzhao, et al.
Published: (2024)

LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
by: Luo, Chuwei, et al.
Published: (2024)

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
by: Wu, Juncheng, et al.
Published: (2026)

Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
by: Deniz, Omer Faruk, et al.
Published: (2026)

NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision
by: Li, Xiang, et al.
Published: (2024)

Correctable Landmark Discovery via Large Models for Vision-Language Navigation
by: Lin, Bingqian, et al.
Published: (2024)

Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks
by: Yang, Zijiao, et al.
Published: (2024)

Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts
by: Nooralahzadeh, Farhad, et al.
Published: (2026)

MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models
by: Xia, Yinan, et al.
Published: (2025)

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

Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
by: Wu, Jiaying, et al.
Published: (2025)

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions
by: Chen, Kai, et al.
Published: (2024)

Where do Large Vision-Language Models Look at when Answering Questions?
by: Xing, Xiaoying, et al.
Published: (2025)

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

Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models
by: Weng, Fenghua, et al.
Published: (2025)

Visual In-Context Learning for Large Vision-Language Models
by: Zhou, Yucheng, et al.
Published: (2024)