Imagen de Portada

PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Yudong, Xie, Ruobing, Chen, Jiansheng, Sun, Xingwu, Wang, Yu
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
por: Zhang, Yudong, et al.
Publicado: (2024)

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

Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs
por: Zhang, Yudong, et al.
Publicado: (2025)

MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
por: Ding, Wei, et al.
Publicado: (2026)

Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
por: Zhang, Yudong, et al.
Publicado: (2024)

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
por: Fu, Yuhan, et al.
Publicado: (2024)

ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformer
por: Sun, Shihua, et al.
Publicado: (2024)

Protego: Detecting Adversarial Examples for Vision Transformers via Intrinsic Capabilities
por: Wu, Jialin, et al.
Publicado: (2025)

Reasoning or Pattern Matching? Probing Large Vision-Language Models with Visual Puzzles
por: Lymperaiou, Maria, et al.
Publicado: (2026)

Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models
por: Guo, Qi, et al.
Publicado: (2024)

Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
por: Lan, Bangxiang, et al.
Publicado: (2025)

The Security Threat of Compressed Projectors in Large Vision-Language Models
por: Zhang, Yudong, et al.
Publicado: (2025)

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

3D Question Answering via only 2D Vision-Language Models
por: Wang, Fengyun, et al.
Publicado: (2025)

When and Where to Attack? Stage-wise Attention-Guided Adversarial Attack on Large Vision Language Models
por: Kwak, Jaehyun, et al.
Publicado: (2026)

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
por: Jiang, Zhangqi, et al.
Publicado: (2024)

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

IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
por: Yang, Jiabing, et al.
Publicado: (2025)

Attention-aggregated Attack for Boosting the Transferability of Facial Adversarial Examples
por: Li, Jian-Wei, et al.
Publicado: (2025)

RhythmFormer: Extracting Patterned rPPG Signals based on Periodic Sparse Attention
por: Zou, Bochao, et al.
Publicado: (2024)

D-Attn: Decomposed Attention for Large Vision-and-Language Models
por: Kuo, Chia-Wen, et al.
Publicado: (2025)

Probing Perceptual Constancy in Large Vision-Language Models
por: Sun, Haoran, et al.
Publicado: (2025)

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
por: Cao, Yiming, et al.
Publicado: (2025)

Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning
por: Park, Dongmin, et al.
Publicado: (2024)

TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
por: Wang, Xin, et al.
Publicado: (2026)

On the Adversarial Robustness of 3D Large Vision-Language Models
por: Liu, Chao, et al.
Publicado: (2026)

Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples
por: Howard, Phillip, et al.
Publicado: (2026)

Adversarial Attention Perturbations for Large Object Detection Transformers
por: Yahn, Zachary, et al.
Publicado: (2025)

Structural Graph Probing of Vision-Language Models
por: He, Haoyu, et al.
Publicado: (2026)

SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples
por: Howard, Phillip, et al.
Publicado: (2023)

Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach
por: Guan, Jiwei, et al.
Publicado: (2024)

Magnifier Prompt: Tackling Multimodal Hallucination via Extremely Simple Instructions
por: Fu, Yuhan, et al.
Publicado: (2024)

SegTrans: Transferable Adversarial Examples for Segmentation Models
por: Song, Yufei, et al.
Publicado: (2025)

FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
por: Zhai, Kun, et al.
Publicado: (2025)

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

Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling
por: Zhao, Shiji, et al.
Publicado: (2026)

PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset
por: Liu, Jiazhen, et al.
Publicado: (2024)

Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks
por: Xie, Peng, et al.
Publicado: (2024)

Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow
por: Zhao, Jianfei, et al.
Publicado: (2025)

Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly Detection
por: Qian, Kun, et al.
Publicado: (2024)