DiffBreak: Is Diffusion-Based Purification Robust?
Fuente:
arXiv
Guardado en:
| Autores principales: | Kassis, Andre, Hengartner, Urs, Yu, Yaoliang |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
UnMarker: A Universal Attack on Defensive Image Watermarking
por: Kassis, Andre, et al.
Publicado: (2024)
por: Kassis, Andre, et al.
Publicado: (2024)
DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
por: Wang, Hanrui, et al.
Publicado: (2025)
por: Wang, Hanrui, et al.
Publicado: (2025)
Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
por: Shpilevskiy, Frederick, et al.
Publicado: (2025)
por: Shpilevskiy, Frederick, et al.
Publicado: (2025)
Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models
por: Li, Wenda, et al.
Publicado: (2024)
por: Li, Wenda, et al.
Publicado: (2024)
Robust Classification via a Single Diffusion Model
por: Chen, Huanran, et al.
Publicado: (2023)
por: Chen, Huanran, et al.
Publicado: (2023)
Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
por: Hong, Sanghyun, et al.
Publicado: (2024)
por: Hong, Sanghyun, et al.
Publicado: (2024)
Certified but Fooled! Breaking Certified Defences with Ghost Certificates
por: Vo, Quoc Viet, et al.
Publicado: (2025)
por: Vo, Quoc Viet, et al.
Publicado: (2025)
VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
por: Chou, Sheng-Yen, et al.
Publicado: (2023)
por: Chou, Sheng-Yen, et al.
Publicado: (2023)
Certified Robustness to Data Poisoning in Gradient-Based Training
por: Sosnin, Philip, et al.
Publicado: (2024)
por: Sosnin, Philip, et al.
Publicado: (2024)
Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash
por: Struppek, Lukas, et al.
Publicado: (2021)
por: Struppek, Lukas, et al.
Publicado: (2021)
FLARE: Toward Universal Dataset Purification against Backdoor Attacks
por: Hou, Linshan, et al.
Publicado: (2024)
por: Hou, Linshan, et al.
Publicado: (2024)
On the Multi-modal Vulnerability of Diffusion Models
por: Yang, Dingcheng, et al.
Publicado: (2024)
por: Yang, Dingcheng, et al.
Publicado: (2024)
Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection
por: Gao, Zheng, et al.
Publicado: (2026)
por: Gao, Zheng, et al.
Publicado: (2026)
Latent Code Augmentation Based on Stable Diffusion for Data-free Substitute Attacks
por: Shao, Mingwen, et al.
Publicado: (2023)
por: Shao, Mingwen, et al.
Publicado: (2023)
Extracting Training Data from Unconditional Diffusion Models
por: Chen, Yunhao, et al.
Publicado: (2024)
por: Chen, Yunhao, et al.
Publicado: (2024)
Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluation
por: Wang, Yongyu, et al.
Publicado: (2024)
por: Wang, Yongyu, et al.
Publicado: (2024)
Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks
por: Zimmer, Pascal, et al.
Publicado: (2023)
por: Zimmer, Pascal, et al.
Publicado: (2023)
Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation
por: He, Yuhao, et al.
Publicado: (2025)
por: He, Yuhao, et al.
Publicado: (2025)
Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks using Hyperparameter Tuning
por: Zimmer, Pascal, et al.
Publicado: (2025)
por: Zimmer, Pascal, et al.
Publicado: (2025)
Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing
por: Huang, Yilong, et al.
Publicado: (2026)
por: Huang, Yilong, et al.
Publicado: (2026)
Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
por: Yu, Daiwei, et al.
Publicado: (2024)
por: Yu, Daiwei, et al.
Publicado: (2024)
SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
por: Zhang, Xin, et al.
Publicado: (2026)
por: Zhang, Xin, et al.
Publicado: (2026)
DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
por: Cui, Yingqian, et al.
Publicado: (2023)
por: Cui, Yingqian, et al.
Publicado: (2023)
Certifiably Robust Image Watermark
por: Jiang, Zhengyuan, et al.
Publicado: (2024)
por: Jiang, Zhengyuan, et al.
Publicado: (2024)
Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
por: Zhang, Yechao, et al.
Publicado: (2023)
por: Zhang, Yechao, et al.
Publicado: (2023)
WAVES: Benchmarking the Robustness of Image Watermarks
por: An, Bang, et al.
Publicado: (2024)
por: An, Bang, et al.
Publicado: (2024)
Invisible Backdoor Attacks on Diffusion Models
por: Li, Sen, et al.
Publicado: (2024)
por: Li, Sen, et al.
Publicado: (2024)
Agnostic Multi-Robust Learning Using ERM
por: Ahmadi, Saba, et al.
Publicado: (2023)
por: Ahmadi, Saba, et al.
Publicado: (2023)
Diffence: Fencing Membership Privacy With Diffusion Models
por: Peng, Yuefeng, et al.
Publicado: (2023)
por: Peng, Yuefeng, et al.
Publicado: (2023)
Model Inversion Robustness: Can Transfer Learning Help?
por: Ho, Sy-Tuyen, et al.
Publicado: (2024)
por: Ho, Sy-Tuyen, et al.
Publicado: (2024)
Robust width: A lightweight and certifiable adversarial defense
por: Peck, Jonathan, et al.
Publicado: (2024)
por: Peck, Jonathan, et al.
Publicado: (2024)
SPDMark: Selective Parameter Displacement for Robust Video Watermarking
por: Fares, Samar, et al.
Publicado: (2025)
por: Fares, Samar, et al.
Publicado: (2025)
Identity-Focused Inference and Extraction Attacks on Diffusion Models
por: Vora, Jayneel, et al.
Publicado: (2024)
por: Vora, Jayneel, et al.
Publicado: (2024)
PriSampler: Mitigating Property Inference of Diffusion Models
por: Hu, Hailong, et al.
Publicado: (2023)
por: Hu, Hailong, et al.
Publicado: (2023)
Towards Accurate and Robust Architectures via Neural Architecture Search
por: Ou, Yuwei, et al.
Publicado: (2024)
por: Ou, Yuwei, et al.
Publicado: (2024)
Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
por: Deng, Jieren, et al.
Publicado: (2024)
por: Deng, Jieren, et al.
Publicado: (2024)
Robust image classification with multi-modal large language models
por: Villani, Francesco, et al.
Publicado: (2024)
por: Villani, Francesco, et al.
Publicado: (2024)
Toward Robust Non-Transferable Learning: A Survey and Benchmark
por: Hong, Ziming, et al.
Publicado: (2025)
por: Hong, Ziming, et al.
Publicado: (2025)
Assessing Neural Network Robustness via Adversarial Pivotal Tuning
por: Christensen, Peter Ebert, et al.
Publicado: (2022)
por: Christensen, Peter Ebert, et al.
Publicado: (2022)
SIDE: Surrogate Conditional Data Extraction from Diffusion Models
por: Chen, Yunhao, et al.
Publicado: (2024)
por: Chen, Yunhao, et al.
Publicado: (2024)
Ejemplares similares
-
UnMarker: A Universal Attack on Defensive Image Watermarking
por: Kassis, Andre, et al.
Publicado: (2024) -
DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
por: Wang, Hanrui, et al.
Publicado: (2025) -
Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
por: Shpilevskiy, Frederick, et al.
Publicado: (2025) -
Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models
por: Li, Wenda, et al.
Publicado: (2024) -
Robust Classification via a Single Diffusion Model
por: Chen, Huanran, et al.
Publicado: (2023)