Cover Image

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zhiqiang, Liu, Dongrui, Li, Yan, Ying, Zonghao, Xue, Wei, Luo, Wenhan, Guo, Yike
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models
by: Yakun, Cui, et al.
Published: (2026)

SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion Model
by: Li, Yan, et al.
Published: (2024)

MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
by: Li, Chenxi, et al.
Published: (2025)

From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG
by: Han, Jiaju, et al.
Published: (2026)

CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing
by: Li, Yan, et al.
Published: (2025)

Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge
by: Cai, Yiyang, et al.
Published: (2024)

VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer
by: Liu, Xinyu, et al.
Published: (2025)

Attention Hijackers: Detect and Disentangle Attention Hijacking in LVLMs for Hallucination Mitigation
by: Chen, Beitao, et al.
Published: (2025)

Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking
by: Li, Jingru, et al.
Published: (2026)

Attention! Your Vision Language Model Could Be Maliciously Manipulated
by: Wang, Xiaosen, et al.
Published: (2025)

A-VL: Adaptive Attention for Large Vision-Language Models
by: Zhang, Junyang, et al.
Published: (2024)

Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
by: Zhang, Juntian, et al.
Published: (2025)

Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention
by: Li, Mengfei, et al.
Published: (2024)

Freeze the backbones: A Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-training
by: Qin, Jiuming, et al.
Published: (2024)

QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
by: Zhang, Yudong, et al.
Published: (2025)

Rethinking Causal Mask Attention for Vision-Language Inference
by: Pei, Xiaohuan, et al.
Published: (2025)

One Last Attention for Your Vision-Language Model
by: Chen, Liang, et al.
Published: (2025)

VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking
by: Fu, Jiyuan, et al.
Published: (2026)

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

WalkVLM:Aid Visually Impaired People Walking by Vision Language Model
by: Yuan, Zhiqiang, et al.
Published: (2024)

Large Vision-Language Models Get Lost in Attention
by: Xi, Gongli, et al.
Published: (2026)

Attention Prompting on Image for Large Vision-Language Models
by: Yu, Runpeng, et al.
Published: (2024)

ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics
by: Wei, Ziyu, et al.
Published: (2026)

Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models
by: Im, Eun Woo, et al.
Published: (2025)

STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference
by: Guo, Yichen, et al.
Published: (2025)

GeoWorld-VLM: Geometry from World Models for Vision-Language Models
by: Gu, Renjie, et al.
Published: (2026)

Physically Grounded Vision-Language Models for Robotic Manipulation
by: Gao, Jensen, et al.
Published: (2023)

Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation
by: Zhang, Jihai, et al.
Published: (2025)

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
by: Tang, Zhenwei, et al.
Published: (2025)

Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
by: Zhang, Jie, et al.
Published: (2025)

Scale-Aware Curriculum Learning for Ddata-Efficient Lung Nodule Detection with YOLOv11
by: Luo, Yi, et al.
Published: (2025)

Breaking Self-Attention Failure: Rethinking Query Initialization for Infrared Small Target Detection
by: Liu, Yuteng, et al.
Published: (2026)

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models
by: Choi, Dasol, et al.
Published: (2026)

Leveraging Vision-Language Models to Detect Attention in Educational Videos
by: Becquet, Gabriel, et al.
Published: (2026)

Learning to Look: Cognitive Attention Alignment with Vision-Language Models
by: Yang, Ryan L., et al.
Published: (2025)

Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
by: Zhang, Naifu, et al.
Published: (2025)

QueryAdapter: Rapid Adaptation of Vision-Language Models in Response to Natural Language Queries
by: Chapman, Nicolas Harvey, et al.
Published: (2025)

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
by: Woo, Sangmin, et al.
Published: (2024)

Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework
by: Wang, Shaobo, et al.
Published: (2023)

ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models
by: Yang, Cheng, et al.
Published: (2026)