Copertina

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Yiming, Liu, Kezhao, Xiao, Yao, Dong, Ziyi, Xu, Xiaogang, Wei, Pengxu, Lin, Liang
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Decoder-Only LLMs are Better Controllers for Diffusion Models
di: Dong, Ziyi, et al.
Pubblicazione: (2025)

DreamArtist++: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter
di: Dong, Ziyi, et al.
Pubblicazione: (2022)

When Preference Labels Fall Short: Aligning Diffusion Models from Real Data
di: Chen, Weiyan, et al.
Pubblicazione: (2026)

Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
di: Li, Yiquan, et al.
Pubblicazione: (2024)

Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention into Convolutions
di: Dong, ZiYi, et al.
Pubblicazione: (2025)

Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior
di: Shi, Yukai, et al.
Pubblicazione: (2024)

Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection
di: Xiao, Yao, et al.
Pubblicazione: (2026)

Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
di: Pei, Gaozheng, et al.
Pubblicazione: (2025)

Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification
di: Sun, Yuhao, et al.
Pubblicazione: (2025)

Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification
di: Yang, Wenkui, et al.
Pubblicazione: (2025)

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness
di: Tang, Yolo Y., et al.
Pubblicazione: (2025)

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding
di: Tang, Jiaqi, et al.
Pubblicazione: (2025)

DiffBreak: Is Diffusion-Based Purification Robust?
di: Kassis, Andre, et al.
Pubblicazione: (2024)

Boosting Diffusion-Based Text Image Super-Resolution Model Towards Generalized Real-World Scenarios
di: Pan, Chenglu, et al.
Pubblicazione: (2025)

Diffusion Noise Feature: Accurate and Fast Generated Image Detection
di: Zhang, Yichi, et al.
Pubblicazione: (2023)

Gradient-Free Adversarial Purification with Diffusion Models
di: Dai, Xuelong, et al.
Pubblicazione: (2025)

Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
di: Zhao, Qing, et al.
Pubblicazione: (2025)

IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images
di: Wang, Meilin, et al.
Pubblicazione: (2024)

Enhancing Facial Privacy Protection via Weakening Diffusion Purification
di: Salar, Ali, et al.
Pubblicazione: (2025)

Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement
di: Xu, Xiaogang, et al.
Pubblicazione: (2025)

Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
di: Meng, Zichong, et al.
Pubblicazione: (2024)

Towards Multimodal Sentiment Analysis Debiasing via Bias Purification
di: Yang, Dingkang, et al.
Pubblicazione: (2024)

Towards Realistic Example-based Modeling via 3D Gaussian Stitching
di: Gao, Xinyu, et al.
Pubblicazione: (2024)

Da Yu: Towards USV-Based Image Captioning for Waterway Surveillance and Scene Understanding
di: Guan, Runwei, et al.
Pubblicazione: (2025)

Robust and Efficient Adversarial Defense in SNNs via Image Purification and Joint Detection
di: Chen, Weiran, et al.
Pubblicazione: (2024)

Controllable Diverse Sampling for Diffusion Based Motion Behavior Forecasting
di: Xu, Yiming, et al.
Pubblicazione: (2024)

CoDefend: Cross-Modal Collaborative Defense via Diffusion Purification and Prompt Optimization
di: Zhu, Fengling, et al.
Pubblicazione: (2025)

Adaptive 1D Video Diffusion Autoencoder
di: Teng, Yao, et al.
Pubblicazione: (2026)

HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models
di: Peng, Xiaogang, et al.
Pubblicazione: (2023)

Towards Memorization-Free Diffusion Models
di: Chen, Chen, et al.
Pubblicazione: (2024)

NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
di: Nan, Junjie, et al.
Pubblicazione: (2025)

SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models
di: Wang, Zilan, et al.
Pubblicazione: (2024)

Adversarial Guided Diffusion Models for Adversarial Purification
di: Lin, Guang, et al.
Pubblicazione: (2024)

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information
di: Zhang, Mingkun, et al.
Pubblicazione: (2024)

Parametric Primitive Analysis of CAD Sketches with Vision Transformer
di: Wang, Xiaogang, et al.
Pubblicazione: (2024)

Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence
di: Yuan, Tianyu, et al.
Pubblicazione: (2025)

Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance
di: Wang, Jiacheng, et al.
Pubblicazione: (2024)

Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance
di: Lin, Yingqi, et al.
Pubblicazione: (2023)

DreamLCM: Towards High-Quality Text-to-3D Generation via Latent Consistency Model
di: Zhong, Yiming, et al.
Pubblicazione: (2024)

Towards Practical Human Motion Prediction with LiDAR Point Clouds
di: Han, Xiao, et al.
Pubblicazione: (2024)