Imagen de Portada

Data-Dependent Stability Analysis of Adversarial Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yihan, Liu, Shuang, Gao, Xiao-Shan
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Game-Theoretic Unlearnable Example Generator
por: Liu, Shuang, et al.
Publicado: (2024)

Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
por: Wang, Yihan, et al.
Publicado: (2024)

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
por: Liu, Shuang, et al.
Publicado: (2025)

BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
por: Wang, Yihan, et al.
Publicado: (2024)

Towards Robust Content Watermarking Against Removal and Forgery Attacks
por: Zhu, Yifan, et al.
Publicado: (2026)

Stability and Generalization in Free Adversarial Training
por: Cheng, Xiwei, et al.
Publicado: (2024)

Scaling Adversarial Training via Data Selection
por: Ye, Youran, et al.
Publicado: (2025)

Stability and Generalization of Adversarial Diffusion Training
por: Hosseini, Hesam, et al.
Publicado: (2025)

Capturing the Temporal Dependence of Training Data Influence
por: Wang, Jiachen T., et al.
Publicado: (2024)

On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars
por: Tao, Chun, et al.
Publicado: (2021)

Extracting Training Data from Diffusion Language Models via Infilling
por: Wang, Yihan, et al.
Publicado: (2026)

Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching
por: Kong, Kyeongbo, et al.
Publicado: (2021)

$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
por: Li, Pengyu, et al.
Publicado: (2026)

Ignition Phase : Standard Training for Fast Adversarial Robustness
por: Yu-Hang, Wang, et al.
Publicado: (2025)

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
por: Liu, Chen, et al.
Publicado: (2021)

Uniformly Stable Algorithms for Adversarial Training and Beyond
por: Xiao, Jiancong, et al.
Publicado: (2024)

MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation
por: Wang, Yihan, et al.
Publicado: (2024)

Censor Dependent Variational Inference
por: Liu, Chuanhui, et al.
Publicado: (2025)

Persistent Classification: A New Approach to Stability of Data and Adversarial Examples
por: Bell, Brian, et al.
Publicado: (2024)

Adversarial Training of Reward Models
por: Bukharin, Alexander, et al.
Publicado: (2025)

Provable Watermarking for Data Poisoning Attacks
por: Zhu, Yifan, et al.
Publicado: (2025)

Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
por: Li, Binghui, et al.
Publicado: (2024)

Stability and List-Replicability for Agnostic Learners
por: Blondal, Ari, et al.
Publicado: (2025)

Stability of Data-Dependent Ridge-Regularization for Inverse Problems
por: Neumayer, Sebastian, et al.
Publicado: (2024)

Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
por: Yu, Lijia, et al.
Publicado: (2024)

Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation
por: Nieth, Björn, et al.
Publicado: (2024)

Conflict-Aware Adversarial Training
por: Xue, Zhiyu, et al.
Publicado: (2024)

Adversarial Training: A Survey
por: Zhao, Mengnan, et al.
Publicado: (2024)

Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds
por: Tuci, Mario, et al.
Publicado: (2025)

Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training
por: Wu, Zihui, et al.
Publicado: (2022)

Adversarial Dependence Minimization
por: De Plaen, Pierre-François, et al.
Publicado: (2025)

Adversarial Attacks on Data Attribution
por: Wang, Xinhe, et al.
Publicado: (2024)

Age-Dependent Heterogeneity in the Association Between Physical Activity and Mental Distress: A Causal Machine Learning Analysis of 3.2 Million U.S. Adults
por: Shan, Yuan
Publicado: (2026)

TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
por: YuHang, Wang, et al.
Publicado: (2025)

Adaptive Learning of the Latent Space of Wasserstein Generative Adversarial Networks
por: Qiu, Yixuan, et al.
Publicado: (2024)

Adversarial Training for Process Reward Models
por: Juneja, Gurusha, et al.
Publicado: (2025)

UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems
por: Zhang, Jingyu, et al.
Publicado: (2026)

A Novel Dependency Framework for Enhancing Discourse Data Analysis
por: Sun, Kun, et al.
Publicado: (2024)

Is Adversarial Training with Compressed Datasets Effective?
por: Chen, Tong, et al.
Publicado: (2024)

Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
por: Aerni, Michael, et al.
Publicado: (2024)