Buchumschlag

Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Shen, Xuelin, Xu, Jiayin, Yin, Kangsheng, Yang, Wenhan
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision
von: Yin, Kangsheng, et al.
Veröffentlicht: (2025)

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
von: Ishmam, Alvi Md, et al.
Veröffentlicht: (2024)

Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
von: Shen, Xuelin, et al.
Veröffentlicht: (2025)

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
von: Zou, Quanchen, et al.
Veröffentlicht: (2026)

FaceShield: Defending Facial Image against Deepfake Threats
von: Jeong, Jaehwan, et al.
Veröffentlicht: (2024)

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
von: Wang, Zhongqi, et al.
Veröffentlicht: (2024)

Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks
von: Wang, Han, et al.
Veröffentlicht: (2024)

Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models
von: Shen, Haozhan, et al.
Veröffentlicht: (2026)

Revisiting Prompt Pretraining of Vision-Language Models
von: Chen, Zhenyuan, et al.
Veröffentlicht: (2024)

EasyOmnimatte: Taming Pretrained Inpainting Diffusion Models for End-to-End Video Layered Decomposition
von: Hu, Yihan, et al.
Veröffentlicht: (2025)

GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
von: Yang, Yijun, et al.
Veröffentlicht: (2024)

Defending Against Frequency-Based Attacks with Diffusion Models
von: Amerehi, Fatemeh, et al.
Veröffentlicht: (2025)

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

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
von: Aladawi, Aljalila, et al.
Veröffentlicht: (2026)

3D Vision and Language Pretraining with Large-Scale Synthetic Data
von: Yang, Dejie, et al.
Veröffentlicht: (2024)

Granular Privacy Control for Geolocation with Vision Language Models
von: Mendes, Ethan, et al.
Veröffentlicht: (2024)

Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior
von: Yu, Yi, et al.
Veröffentlicht: (2024)

SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models
von: Zou, Shu, et al.
Veröffentlicht: (2025)

PixelHacker: Image Inpainting with Structural and Semantic Consistency
von: Xu, Ziyang, et al.
Veröffentlicht: (2025)

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
von: Zhou, Qi, et al.
Veröffentlicht: (2024)

VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compression
von: Sargent, Kyle, et al.
Veröffentlicht: (2025)

VLS: Steering Pretrained Robot Policies via Vision-Language Models
von: Liu, Shuo, et al.
Veröffentlicht: (2026)

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
von: Jin, Yang, et al.
Veröffentlicht: (2023)

Time Traveling to Defend Against Adversarial Example Attacks in Image Classification
von: Etim, Anthony, et al.
Veröffentlicht: (2024)

SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
von: Du, Lingyu, et al.
Veröffentlicht: (2025)

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
von: Cao, Sihan, et al.
Veröffentlicht: (2026)

CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging
von: Kumar, Ashwin, et al.
Veröffentlicht: (2026)

Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models
von: Wang, Zhongqi, et al.
Veröffentlicht: (2025)

Redundancy-Aware Pretraining of Vision-Language Foundation Models in Remote Sensing
von: Adler, Mathis Jürgen, et al.
Veröffentlicht: (2025)

PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
von: Yang, Chenyu, et al.
Veröffentlicht: (2024)

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
von: Cui, Yingqian, et al.
Veröffentlicht: (2023)

SLIP: Structural-aware Language-Image Pretraining for Vision-Language Alignment
von: Lu, Wenbo
Veröffentlicht: (2025)

Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation
von: Yang, Hongji, et al.
Veröffentlicht: (2025)

VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
von: Maruf, M., et al.
Veröffentlicht: (2024)

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection
von: Strack, Lukas, et al.
Veröffentlicht: (2023)

Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Models
von: Meng, Tian, et al.
Veröffentlicht: (2024)

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
von: Chew, Oscar, et al.
Veröffentlicht: (2024)

Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples
von: Wang, Yeyuan, et al.
Veröffentlicht: (2024)

Lost in Distortion: Uncovering the Domain Gap Between Computer Vision and Brain Imaging -- A Study on Pretraining for Age Prediction
von: Zhang, Yanteng, et al.
Veröffentlicht: (2025)

ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
von: Zhou, Zhongyi, et al.
Veröffentlicht: (2025)