Imagen de Portada

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Amini, Sajjad, Teymoorianfard, Mohammadreza, Ma, Shiqing, Houmansadr, Amir
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VIDSTAMP: A Temporally-Aware Watermark for Ownership and Integrity in Video Diffusion Models
por: Teymoorianfard, Mohammadreza, et al.
Publicado: (2025)

Diffence: Fencing Membership Privacy With Diffusion Models
por: Peng, Yuefeng, et al.
Publicado: (2023)

Identifying Models Behind Text-to-Image Leaderboards
por: Naseh, Ali, et al.
Publicado: (2026)

Network-Level Prompt and Trait Leakage in Local Research Agents
por: Jeong, Hyejun, et al.
Publicado: (2025)

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images
por: Naseh, Ali, et al.
Publicado: (2024)

DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformers
por: Yehezkel, Oryan, et al.
Publicado: (2024)

DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
por: Wang, Zhenting, et al.
Publicado: (2023)

Certified Robustness to Data Poisoning in Gradient-Based Training
por: Sosnin, Philip, et al.
Publicado: (2024)

Enhancing Adversarial Example Detection Through Model Explanation
por: Ma, Qian, et al.
Publicado: (2025)

Extracting Training Data from Unconditional Diffusion Models
por: Chen, Yunhao, et al.
Publicado: (2024)

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
por: Jiang, Tanqiu, et al.
Publicado: (2025)

Backdoor Attack with Sparse and Invisible Trigger
por: Gao, Yinghua, et al.
Publicado: (2023)

Sparse and Transferable Universal Singular Vectors Attack
por: Kuvshinova, Kseniia, et al.
Publicado: (2024)

On the Privacy Effect of Data Enhancement via the Lens of Memorization
por: Li, Xiao, et al.
Publicado: (2022)

Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures
por: Dibbo, Sayanton V., et al.
Publicado: (2024)

Improving Adversarial Robustness via Feature Pattern Consistency Constraint
por: Hu, Jiacong, et al.
Publicado: (2024)

The Impact of Scaling Training Data on Adversarial Robustness
por: Zimmerli, Marco, et al.
Publicado: (2025)

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
por: Cheng, Siyuan, et al.
Publicado: (2024)

Enhancing Adversarial Robustness in SNNs with Sparse Gradients
por: Liu, Yujia, et al.
Publicado: (2024)

Certifiably Robust Image Watermark
por: Jiang, Zhengyuan, et al.
Publicado: (2024)

Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples
por: Yilmaz, Eda, et al.
Publicado: (2024)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
por: Zhang, Yimeng, et al.
Publicado: (2024)

Enabling Heterogeneous Adversarial Transferability via Feature Permutation Attacks
por: Wu, Tao, et al.
Publicado: (2025)

WAVES: Benchmarking the Robustness of Image Watermarks
por: An, Bang, et al.
Publicado: (2024)

Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
por: Ba, Zhongjie, et al.
Publicado: (2025)

From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation
por: Nanfack, Geraldin, et al.
Publicado: (2024)

Adversarial Training against Location-Optimized Adversarial Patches
por: Rao, Sukrut, et al.
Publicado: (2020)

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

Agnostic Multi-Robust Learning Using ERM
por: Ahmadi, Saba, et al.
Publicado: (2023)

Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
por: Wu, Shangbo, et al.
Publicado: (2025)

SnatchML: Hijacking ML models without Training Access
por: Ghorbel, Mahmoud, et al.
Publicado: (2024)

Adversarial Training in Low-Label Regimes with Margin-Based Interpolation
por: Ye, Tian, et al.
Publicado: (2024)

SPDMark: Selective Parameter Displacement for Robust Video Watermarking
por: Fares, Samar, et al.
Publicado: (2025)

Robust Classification via a Single Diffusion Model
por: Chen, Huanran, et al.
Publicado: (2023)

Model Inversion Robustness: Can Transfer Learning Help?
por: Ho, Sy-Tuyen, et al.
Publicado: (2024)

Robust width: A lightweight and certifiable adversarial defense
por: Peck, Jonathan, et al.
Publicado: (2024)

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
por: Cheng, Siyuan, et al.
Publicado: (2024)

Crafter: Facial Feature Crafting against Inversion-based Identity Theft on Deep Models
por: Wang, Shiming, et al.
Publicado: (2024)

DataFreeShield: Defending Adversarial Attacks without Training Data
por: Lee, Hyeyoon, et al.
Publicado: (2024)

Privacy-Preserving CNN Training with Transfer Learning: Multiclass Logistic Regression
por: Chiang, John
Publicado: (2023)