Cover Image

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Chen, Huang, Zhichao, Salzmann, Mathieu, Zhang, Tong, Süsstrunk, Sabine
Format:	Preprint
Published:	2021
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Weight Space Representation Learning via Neural Field Adaptation
by: Yang, Zhuoqian, et al.
Published: (2025)

OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation
by: Ozaydin, Baran, et al.
Published: (2024)

Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Density
by: Li, Shuangqi, et al.
Published: (2024)

The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness
by: Hao, Yifan, et al.
Published: (2024)

Benign Overfitting in Adversarial Training for Vision Transformers
by: Zhang, Jiaming, et al.
Published: (2026)

Subtractive Modulative Network with Learnable Periodic Activations
by: Wang, Tiou, et al.
Published: (2026)

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
by: Lin, Runqi, et al.
Published: (2024)

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

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
by: Zhao, Mengnan, et al.
Published: (2026)

On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics
by: Li, Binghui, et al.
Published: (2023)

Adversarial Instance Generation and Robust Training for Neural Combinatorial Optimization with Multiple Objectives
by: Liu, Wei, et al.
Published: (2026)

Adversarial training of Keyword Spotting to Minimize TTS Data Overfitting
by: Park, Hyun Jin, et al.
Published: (2024)

DSI2I: Dense Style for Unpaired Image-to-Image Translation
by: Ozaydin, Baran, et al.
Published: (2022)

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

Promoting Generalization for Exact Solvers via Adversarial Instance Augmentation
by: Liu, Haoyang, et al.
Published: (2023)

Canonical Latent Representations in Conditional Diffusion Models
by: Xu, Yitao, et al.
Published: (2025)

Adversarial Testing as a Tool for Interpretability: Length-based Overfitting of Elementary Functions in Transformers
by: Zavoral, Patrik, et al.
Published: (2024)

Learning Adversarial MDPs with Stochastic Hard Constraints
by: Stradi, Francesco Emanuele, et al.
Published: (2024)

Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless $l^p$ Norm Solution for Fast Adversarial Training
by: Mehouachi, Fares B., et al.
Published: (2025)

LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution
by: Li, Shuangqi, et al.
Published: (2026)

Low-Cost Hard-Label Adversarial Attack with Theoretical Foundations
by: Liu, Jun, et al.
Published: (2026)

Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
by: Hou, Zhichao, et al.
Published: (2025)

Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing
by: Zhong, Xuyang, et al.
Published: (2025)

TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction
by: Aydemir, Bahar, et al.
Published: (2023)

Data Augmentation via Latent Diffusion for Saliency Prediction
by: Aydemir, Bahar, et al.
Published: (2024)

Adversarial Training of Reward Models
by: Bukharin, Alexander, et al.
Published: (2025)

Data-Dependent Stability Analysis of Adversarial Training
by: Wang, Yihan, et al.
Published: (2024)

Adversarial Training: A Survey
by: Zhao, Mengnan, et al.
Published: (2024)

Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning
by: Khan, Hikmat, et al.
Published: (2024)

Enhancing Adversarial Training via Reweighting Optimization Trajectory
by: Huang, Tianjin, et al.
Published: (2023)

QT-DoG: Quantization-aware Training for Domain Generalization
by: Javed, Saqib, et al.
Published: (2024)

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

Learning to Weight Parameters for Training Data Attribution
by: Li, Shuangqi, et al.
Published: (2025)

Vulnerability-Aware Robust Multimodal Adversarial Training
by: Zhang, Junrui, et al.
Published: (2025)

Boosting Adversarial Robustness and Generalization with Structural Prior
by: Hou, Zhichao, et al.
Published: (2025)

MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
by: Mahdi, Soroush, et al.
Published: (2025)

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
by: Jin, Zhibo, et al.
Published: (2024)

Explanation-Guided Adversarial Training for Robust and Interpretable Models
by: Chen, Chao, et al.
Published: (2026)

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

S2O: Enhancing Adversarial Training with Second-Order Statistics of Weights
by: Jin, Gaojie, et al.
Published: (2026)