Imagen de Portada

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zheng, Weijie, Ma, Xingjun, Huang, Hanxun, Wu, Zuxuan, Jiang, Yu-Gang
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

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
por: Huang, Hanxun, et al.
Publicado: (2025)

Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
por: Xie, Yong, et al.
Publicado: (2024)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
por: Cui, Kaiyuan, et al.
Publicado: (2026)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
por: Li, Jiayu, et al.
Publicado: (2025)

Targeted Downstream-Agnostic Attack
por: Lei, Zhuxin, et al.
Publicado: (2026)

Pre-Trained Model Recommendation for Downstream Fine-tuning
por: Bai, Jiameng, et al.
Publicado: (2024)

Transferable Adversarial Attacks on SAM and Its Downstream Models
por: Xia, Song, et al.
Publicado: (2024)

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
por: Zhao, Yunhan, et al.
Publicado: (2025)

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
por: Zhao, Yunhan, et al.
Publicado: (2024)

A Two-Stage Globally-Diverse Adversarial Attack for Vision-Language Pre-training Models
por: Chen, Wutao, et al.
Publicado: (2026)

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
por: Chen, Hao, et al.
Publicado: (2023)

Adversarial Prompt Distillation for Vision-Language Models
por: Luo, Lin, et al.
Publicado: (2024)

Advancing ALS Applications with Large-Scale Pre-training: Dataset Development and Downstream Assessment
por: Xiu, Haoyi, et al.
Publicado: (2025)

Adversarial Prompt Tuning for Vision-Language Models
por: Zhang, Jiaming, et al.
Publicado: (2023)

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
por: Li, Teng, et al.
Publicado: (2025)

Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack
por: Liu, Xin, et al.
Publicado: (2025)

Transferable Adversarial Face Attack with Text Controlled Attribute
por: Li, Wenyun, et al.
Publicado: (2024)

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
por: Zhang, Jiaming, et al.
Publicado: (2025)

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
por: Liu, Han, et al.
Publicado: (2026)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
por: Li, Juncheng, et al.
Publicado: (2025)

Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
por: Lin, Honglin, et al.
Publicado: (2026)

Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks
por: Ding, Yuhe, et al.
Publicado: (2024)

T2UE: Generating Unlearnable Examples from Text Descriptions
por: Ma, Xingjun, et al.
Publicado: (2025)

VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
por: Si, Shengyu, et al.
Publicado: (2026)

A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models
por: Zheng, Haonan, et al.
Publicado: (2024)

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
por: Sun, Ye, et al.
Publicado: (2026)

Black-box Membership Inference Attacks on the Pre-training Data of Image-generation Models
por: Qi, Tao, et al.
Publicado: (2026)

SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models
por: Tahboub, Hamza, et al.
Publicado: (2025)

White-box Multimodal Jailbreaks Against Large Vision-Language Models
por: Wang, Ruofan, et al.
Publicado: (2024)

What Sketch Explainability Really Means for Downstream Tasks
por: Bandyopadhyay, Hmrishav, et al.
Publicado: (2024)

Generative Pre-trained Autoregressive Diffusion Transformer
por: Zhang, Yuan, et al.
Publicado: (2025)

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

Feedback-based Modal Mutual Search for Attacking Vision-Language Pre-training Models
por: Ding, Renhua, et al.
Publicado: (2024)

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

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
por: Kowalczuk, Antoni, et al.
Publicado: (2024)

VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models
por: Mei, Hefei, et al.
Publicado: (2025)

Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving
por: Wang, Lu, et al.
Publicado: (2025)

When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models
por: Lu, Hui, et al.
Publicado: (2025)

Benchmarking Gaslighting Negation Attacks Against Reasoning Models
por: Zhu, Bin, et al.
Publicado: (2025)

CoMP: Continual Multimodal Pre-training for Vision Foundation Models
por: Chen, Yitong, et al.
Publicado: (2025)