Image de couverture de livre

DP^2-VL: Private Photo Dataset Protection by Data Poisoning for Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Miao, Hongyi, Jia, Jun, Wang, Xincheng, Ma, Qianli, Sun, Wei, Zhou, Wangqiu, Zhu, Dandan, Cao, Yewen, Liu, Zhi, Zhai, Guangtao
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation
par: Jia, Jun, et autres
Publié: (2025)

DLADiff: A Dual-Layer Defense Framework against Fine-Tuning and Zero-Shot Customization of Diffusion Models
par: Jia, Jun, et autres
Publié: (2025)

AMIF: Authorizable Medical Image Fusion Model with Built-in Authentication
par: Song, Jie, et autres
Publié: (2026)

Ultrasound-QBench: Can LLMs Aid in Quality Assessment of Ultrasound Imaging?
par: Miao, Hongyi, et autres
Publié: (2025)

DP-GENG : Differentially Private Dataset Distillation Guided by DP-Generated Data
par: Shi, Shuo, et autres
Publié: (2025)

Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach
par: Wang, Xincheng, et autres
Publié: (2025)

Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation
par: Sun, Wei, et autres
Publié: (2025)

Surveillance Facial Image Quality Assessment: A Multi-dimensional Dataset and Lightweight Model
par: Jiang, Yanwei, et autres
Publié: (2026)

Textured Mesh Saliency: Bridging Geometry and Texture for Human Perception in 3D Graphics
par: Zhang, Kaiwei, et autres
Publié: (2024)

Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes
par: Zhang, Kaiwei, et autres
Publié: (2025)

CompressedVQA-HDR: Generalized Full-reference and No-reference Quality Assessment Models for Compressed High Dynamic Range Videos
par: Sun, Wei, et autres
Publié: (2025)

FlashDP: Private Training Large Language Models with Efficient DP-SGD
par: Wang, Liangyu, et autres
Publié: (2025)

LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
par: Huang, Jiangyong, et autres
Publié: (2025)

VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning
par: Cao, Linhan, et autres
Publié: (2025)

Generalizable Video Quality Assessment via Weak-to-Strong Learning
par: Cao, Linhan, et autres
Publié: (2025)

QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding
par: Cao, Linhan, et autres
Publié: (2026)

Bumblebee cosmology: Tests using distance- and time-redshift probes
par: Zhu, Xincheng, et autres
Publié: (2024)

ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning
par: Yao, Xincheng, et autres
Publié: (2025)

ResAD: A Simple Framework for Class Generalizable Anomaly Detection
par: Yao, Xincheng, et autres
Publié: (2024)

DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting
par: Li, Mingchen, et autres
Publié: (2025)

VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
par: Zhang, Jipeng, et autres
Publié: (2025)

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
par: Zhang, Yongting, et autres
Publié: (2024)

GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI
par: Li, Tianbin, et autres
Publié: (2024)

Vision-Language Consistency Guided Multi-modal Prompt Learning for Blind AI Generated Image Quality Assessment
par: Fu, Jun, et autres
Publié: (2024)

Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark
par: Zhou, Rulin, et autres
Publié: (2025)

DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators
par: Afonja, Tejumade, et autres
Publié: (2024)

Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning
par: Assumpcao, Nicolas Riccieri Gardin, et autres
Publié: (2025)

VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer
par: Zhong, Humen, et autres
Publié: (2024)

Defense against Poisoning Attacks under Shuffle-DP
par: Wang, Siyi, et autres
Publié: (2026)

BioVL-QR: Egocentric Biochemical Vision-and-Language Dataset Using Micro QR Codes
par: Nishimoto, Tomohiro, et autres
Publié: (2024)

SemDP: Semantic-level Differential Privacy Protection for Face Datasets
par: Zhang, Xiaoting, et autres
Publié: (2024)

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models
par: Dong, Daxiang, et autres
Publié: (2025)

DP-OPD: Differentially Private On-Policy Distillation for Language Models
par: Khadem, Fatemeh, et autres
Publié: (2026)

DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models
par: Liu, Jin, et autres
Publié: (2026)

Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
par: Cahyawijaya, Samuel, et autres
Publié: (2025)

Data Poisoning Attacks to Locally Differentially Private Range Query Protocols
par: Liao, Ting-Wei, et autres
Publié: (2025)

How Private are DP-SGD Implementations?
par: Chua, Lynn, et autres
Publié: (2024)

SingingHead: A Large-scale 4D Dataset for Singing Head Animation
par: Wu, Sijing, et autres
Publié: (2023)

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
par: Lin, Miao, et autres
Publié: (2026)

Agile Affine Frequency Division Multiplexing
par: Cao, Yewen, et autres
Publié: (2025)