Imagen de Portada

Robustness of Vision Foundation Models to Common Perturbations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Hongbin, Jiang, Zhengyuan, Hong, Cheng, Gong, Neil Zhenqiang
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SafeText: Safe Text-to-image Models via Aligning the Text Encoder
por: Hu, Yuepeng, et al.
Publicado: (2025)

Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models
por: Liu, Hongbin, et al.
Publicado: (2024)

Certifiably Robust Image Watermark
por: Jiang, Zhengyuan, et al.
Publicado: (2024)

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
por: Jia, Yuqi, et al.
Publicado: (2024)

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
por: Zhang, Jinghuai, et al.
Publicado: (2022)

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
por: Jiang, Zhengyuan, et al.
Publicado: (2025)

Stable Signature is Unstable: Removing Image Watermark from Diffusion Models
por: Hu, Yuepeng, et al.
Publicado: (2024)

EditTrack: Detecting and Attributing AI-assisted Image Editing
por: Jiang, Zhengyuan, et al.
Publicado: (2025)

VideoMarkBench: Benchmarking Robustness of Video Watermarking
por: Jiang, Zhengyuan, et al.
Publicado: (2025)

Refusing Safe Prompts for Multi-modal Large Language Models
por: Shao, Zedian, et al.
Publicado: (2024)

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
por: Shao, Zedian, et al.
Publicado: (2026)

Watermark-based Attribution of AI-Generated Content
por: Jiang, Zhengyuan, et al.
Publicado: (2024)

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

Adversarial Robustness of Vision in Open Foundation Models
por: Fox, Jonathon, et al.
Publicado: (2025)

Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework
por: Yin, Minglei, et al.
Publicado: (2023)

Practical Region-level Attack against Segment Anything Models
por: Shen, Yifan, et al.
Publicado: (2024)

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

AI-generated Image Detection: Passive or Watermark?
por: Guo, Moyang, et al.
Publicado: (2024)

GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
por: Li, Kecen, et al.
Publicado: (2025)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
por: Kim, Hee-Seon, et al.
Publicado: (2024)

When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
por: Tian, Yuan, et al.
Publicado: (2026)

RoMA: Robust Malware Attribution via Byte-level Adversarial Training with Global Perturbations and Adversarial Consistency Regularization
por: Sun, Yuxia, et al.
Publicado: (2025)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
por: Zhang, Yimeng, et al.
Publicado: (2024)

PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning
por: Hussein, Noor, et al.
Publicado: (2024)

Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
por: Ba, Zhongjie, et al.
Publicado: (2025)

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
por: Zhang, Rui, et al.
Publicado: (2025)

From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge
por: Lu, Hui, et al.
Publicado: (2025)

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

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
por: Ying, Zonghao, et al.
Publicado: (2024)

Detecting AutoAttack Perturbations in the Frequency Domain
por: Lorenz, Peter, et al.
Publicado: (2021)

Attacking Transformers with Feature Diversity Adversarial Perturbation
por: Gao, Chenxing, et al.
Publicado: (2024)

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
por: Zhong, Zhiyuan, et al.
Publicado: (2025)

Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
por: Gong, Xueluan, et al.
Publicado: (2024)

MADation: Face Morphing Attack Detection with Foundation Models
por: Caldeira, Eduarda, et al.
Publicado: (2025)

An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers
por: Gong, Xueluan, et al.
Publicado: (2024)

Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
por: Ying, Chengyang, et al.
Publicado: (2022)

Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models
por: Zhang, Zongmin, et al.
Publicado: (2025)

Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey
por: Zhao, Longjie, et al.
Publicado: (2026)

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
por: Gao, Kuofeng, et al.
Publicado: (2024)

Privacy-Preserving Federated Vision Transformer Learning Leveraging Lightweight Homomorphic Encryption in Medical AI
por: Amin, Al, et al.
Publicado: (2025)