Cover Image

Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jiawei, Zuo, Yushen, Chai, Yuanjun, Liu, Zhendong, Fu, Yicheng, Feng, Yichun, Lam, Kin-Man
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization
by: He, Zongqi, et al.
Published: (2025)

Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognition
by: Dong, Rongkang, et al.
Published: (2026)

Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning
by: Zuo, Yushen, et al.
Published: (2024)

Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework
by: He, Zongqi, et al.
Published: (2025)

Vision-Language Model Guided Image Restoration
by: Yang, Cuixin, et al.
Published: (2025)

HFS: Holistic Query-Aware Frame Selection for Efficient Video Reasoning
by: Yang, Yiqing, et al.
Published: (2025)

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
by: Liu, Xinwei, et al.
Published: (2025)

AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection
by: Zhou, Jingchun, et al.
Published: (2023)

SA$^{2}$Net: Scale-Adaptive Structure-Affinity Transformation for Spine Segmentation from Ultrasound Volume Projection Imaging
by: Xie, Hao, et al.
Published: (2025)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
by: Fang, Hao, et al.
Published: (2024)

Point Clouds Are Specialized Images: A Knowledge Transfer Approach for 3D Understanding
by: Kang, Jiachen, et al.
Published: (2023)

Mitigating Cache Noise in Test-Time Adaptation for Large Vision-Language Models
by: Zhai, Haotian, et al.
Published: (2025)

IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning
by: Wang, Jiayao, et al.
Published: (2025)

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation
by: Yang, Hao, et al.
Published: (2026)

LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models
by: Huang, Guolei, et al.
Published: (2025)

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack
by: Liu, Hanqing, et al.
Published: (2025)

Multi-level distortion-aware deformable network for omnidirectional image super-resolution
by: Yang, Cuixin, et al.
Published: (2025)

IA2U: A Transfer Plugin with Multi-Prior for In-Air Model to Underwater
by: Zhou, Jingchun, et al.
Published: (2023)

Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding
by: Wang, Chao, et al.
Published: (2025)

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering
by: Zhang, Xiaohan, et al.
Published: (2025)

Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually
by: Bethany, Mazal, et al.
Published: (2024)

Self-Correction Inside the Model: Leveraging Layer Attention to Mitigate Hallucinations in Large Vision Language Models
by: Fu, April
Published: (2026)

Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
by: Zhao, Zhengyue, et al.
Published: (2023)

Residual Attention Single-Head Vision Transformer Network for Rolling Bearing Fault Diagnosis in Noisy Environments
by: Lai, Songjiang, et al.
Published: (2024)

Universal Camouflage Attack on Vision-Language Models for Autonomous Driving
by: Kong, Dehong, et al.
Published: (2025)

Adversarial Machine Learning: Attacking and Safeguarding Image Datasets
by: Chowdhury, Koushik
Published: (2025)

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
by: Wu, Kai, et al.
Published: (2024)

Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization
by: Peng, Jiangweizhi, et al.
Published: (2024)

Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation
by: Chen, Meng, et al.
Published: (2024)

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
by: Liang, Jiawei, et al.
Published: (2024)

Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models
by: Jang, Jonggyu, et al.
Published: (2024)

One Noise to Rule Them All: Multi-View Adversarial Attacks with Universal Perturbation
by: Ergezer, Mehmet, et al.
Published: (2024)

Dynamic Execution Commitment of Vision-Language-Action Models
by: Chen, Feng, et al.
Published: (2026)

NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
by: Fu, Yonggan, et al.
Published: (2023)

A Navigation Framework Utilizing Vision-Language Models
by: Duan, Yicheng, et al.
Published: (2025)

AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing
by: Hong, Ziming, et al.
Published: (2025)

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
by: Liang, Siyuan, et al.
Published: (2024)

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models
by: Choi, In Chong, et al.
Published: (2026)

Adaptive Perturbation for Adversarial Attack
by: Yuan, Zheng, et al.
Published: (2021)

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