Cover Image

Wide Two-Layer Networks can Learn from Adversarial Perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kumano, Soichiro, Kera, Hiroshi, Yamasaki, Toshihiko
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Theoretical Understanding of Learning from Adversarial Perturbations
by: Kumano, Soichiro, et al.
Published: (2024)

Adversarial Training from Mean Field Perspective
by: Kumano, Soichiro, et al.
Published: (2025)

Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners
by: Kumano, Soichiro, et al.
Published: (2025)

Language-guided Detection and Mitigation of Unknown Dataset Bias
by: Zhao, Zaiying, et al.
Published: (2024)

Adversarially Trained Object Detector for Unsupervised Domain Adaptation
by: Fujii, Kazuma, et al.
Published: (2021)

Learning Moderately Input-Sensitive Functions: A Case Study in QR Code Decoding
by: Yoda, Kazuki, et al.
Published: (2025)

Data-Driven Prediction of Seismic Intensity Distributions Featuring Hybrid Classification-Regression Models
by: Mizutani, Koyu, et al.
Published: (2024)

Reward Incremental Learning in Text-to-Image Generation
by: Wang, Maorong, et al.
Published: (2024)

Dealing with Synthetic Data Contamination in Online Continual Learning
by: Wang, Maorong, et al.
Published: (2024)

Identifying Important Group of Pixels using Interactions
by: Sumiyasu, Kosuke, et al.
Published: (2024)

Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval
by: Xiao, Ling, et al.
Published: (2022)

Continual Distillation of Teachers from Different Domains
by: Michel, Nicolas, et al.
Published: (2026)

Dynamic Epsilon Scheduling: A Multi-Factor Adaptive Perturbation Budget for Adversarial Training
by: Mitkiy, Alan, et al.
Published: (2025)

Detecting Adversarial Data using Perturbation Forgery
by: Wang, Qian, et al.
Published: (2024)

Adversarial Example Defense via Perturbation Grading Strategy
by: Zhu, Shaowei, et al.
Published: (2022)

PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles
by: Brusini, Leonardo, et al.
Published: (2026)

SVasP: Self-Versatility Adversarial Style Perturbation for Cross-Domain Few-Shot Learning
by: Li, Wenqian, et al.
Published: (2024)

SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learning
by: Li, Wenqian, et al.
Published: (2026)

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization
by: Zhang, Yechao, et al.
Published: (2025)

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
by: Zhang, Lilin, et al.
Published: (2026)

SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning
by: Qian, Qi, et al.
Published: (2024)

Understanding Adversarial Robustness from Feature Maps of Convolutional Layers
by: Xu, Cong, et al.
Published: (2022)

Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations
by: Zhang, Haimin, et al.
Published: (2021)

Convergence Analysis of Blurring Mean Shift
by: Yamasaki, Ryoya, et al.
Published: (2024)

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
by: Li, Shuai, et al.
Published: (2024)

Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification
by: Zhuang, Weiwei, et al.
Published: (2026)

Learning Brenier Potentials with Convex Generative Adversarial Neural Networks
by: Drygala, Claudia, et al.
Published: (2025)

Creative Portraiture: Exploring Creative Adversarial Networks and Conditional Creative Adversarial Networks
by: Hereu, Sebastian, et al.
Published: (2024)

Learning from Similarity Proportion Loss for Classifying Skeletal Muscle Recovery Stages
by: Yamaoka, Yu, et al.
Published: (2025)

Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
by: Oskouie, Haniyeh Ehsani, et al.
Published: (2022)

Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learning
by: Hu, Jiyu, et al.
Published: (2025)

A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
by: Xiao, Ling, et al.
Published: (2026)

Face2Diffusion for Fast and Editable Face Personalization
by: Shiohara, Kaede, et al.
Published: (2024)

Unified Vector Floorplan Generation via Markup Representation
by: Shiohara, Kaede, et al.
Published: (2026)

CE-FAM: Concept-Based Explanation via Fusion of Activation Maps
by: Kuroki, Michihiro, et al.
Published: (2025)

BSED: Baseline Shapley-Based Explainable Detector
by: Kuroki, Michihiro, et al.
Published: (2023)

Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQA
by: Zhao, Zaiying, et al.
Published: (2025)

Boosting Adversarial Transferability via Residual Perturbation Attack
by: Peng, Jinjia, et al.
Published: (2025)

Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition
by: Tanaka, Nariki, et al.
Published: (2023)

Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
by: Pavlitska, Svetlana, et al.
Published: (2025)