Copertina

Understanding Adversarial Robustness from Feature Maps of Convolutional Layers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Cong, Zhang, Wei, Wang, Jun, Yang, Min
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Feature Map Similarity Reduction in Convolutional Neural Networks
di: Belmekki, Zakariae, et al.
Pubblicazione: (2024)

Rotation-Robust Regression with Convolutional Model Trees
di: Li, Hongyi, et al.
Pubblicazione: (2026)

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

Robustness Feature Adapter for Efficient Adversarial Training
di: Wu, Quanwei, et al.
Pubblicazione: (2025)

RandAlign: A Parameter-Free Method for Regularizing Graph Convolutional Networks
di: Zhang, Haimin, et al.
Pubblicazione: (2024)

Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning
di: Khan, Sarwar
Pubblicazione: (2024)

Adversarial Examples Are Not Real Features
di: Li, Ang, et al.
Pubblicazione: (2023)

AFD: Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement
di: Zhou, Nuoyan, et al.
Pubblicazione: (2024)

Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness
di: Zhang, Kejia, et al.
Pubblicazione: (2024)

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

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

Pruning Self-attentions into Convolutional Layers in Single Path
di: He, Haoyu, et al.
Pubblicazione: (2021)

ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations
di: Addepalli, Sravanti, et al.
Pubblicazione: (2024)

AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps
di: Hsieh, Chia-Ying, et al.
Pubblicazione: (2026)

Towards Understanding Adversarial Transferability in Federated Learning
di: Li, Yijiang, et al.
Pubblicazione: (2023)

Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation
di: Zhao, Shiji, et al.
Pubblicazione: (2023)

Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training
di: Dong, Junhao, et al.
Pubblicazione: (2024)

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

Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters
di: Warnecke, Alexander, et al.
Pubblicazione: (2026)

Spectral Norm of Convolutional Layers with Circular and Zero Paddings
di: Delattre, Blaise, et al.
Pubblicazione: (2024)

Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
di: Chen, Lu, et al.
Pubblicazione: (2025)

Spatio-temporal Prompting Network for Robust Video Feature Extraction
di: Sun, Guanxiong, et al.
Pubblicazione: (2024)

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
di: Zhang, Yechao, et al.
Pubblicazione: (2023)

Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
di: Liu, Zhenyu, et al.
Pubblicazione: (2024)

Compositional Adversarial Training for Robust Visual Watermarking
di: Satheesh, Anirudh, et al.
Pubblicazione: (2026)

Adversarial Robustness for Deep Learning-based Wildfire Prediction Models
di: Ide, Ryo, et al.
Pubblicazione: (2024)

Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections
di: Zhou, Youwei, et al.
Pubblicazione: (2024)

Bag of Tricks to Boost Adversarial Transferability
di: Zhang, Zeliang, et al.
Pubblicazione: (2024)

RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation
di: Nath, Utkarsh, et al.
Pubblicazione: (2023)

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

Analytic Convolutional Layer: A Step to Analytic Neural Network
di: Cui, Jingmao, et al.
Pubblicazione: (2024)

Towards Adversarially Robust Dataset Distillation by Curvature Regularization
di: Xue, Eric, et al.
Pubblicazione: (2024)

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective
di: Wang, Zhaoxin, et al.
Pubblicazione: (2024)

Identifying and Understanding Cross-Class Features in Adversarial Training
di: Wei, Zeming, et al.
Pubblicazione: (2025)

Wide Two-Layer Networks can Learn from Adversarial Perturbations
di: Kumano, Soichiro, et al.
Pubblicazione: (2024)

Understanding Adversarial Training with Energy-based Models
di: Mirza, Mujtaba Hussain, et al.
Pubblicazione: (2025)

Learning Robust Convolutional Neural Networks with Relevant Feature Focusing via Explanations
di: Adachi, Kazuki, et al.
Pubblicazione: (2022)

A Sober Look at the Robustness of CLIPs to Spurious Features
di: Wang, Qizhou, et al.
Pubblicazione: (2024)

Evaluating the Adversarial Robustness of Detection Transformers
di: Nazeri, Amirhossein, et al.
Pubblicazione: (2024)

Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
di: Xu, Haochuan, et al.
Pubblicazione: (2025)