Cover Image

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Runqi, Yu, Chaojian, Han, Bo, Liu, Tongliang
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
by: Lin, Runqi, et al.
Published: (2024)

Understanding Robust Overfitting from the Feature Generalization Perspective
by: Yu, Chaojian, et al.
Published: (2023)

Instance-dependent Early Stopping
by: Yuan, Suqin, et al.
Published: (2025)

FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction
by: Lin, Runqi, et al.
Published: (2025)

Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning
by: Huang, Zhuo, et al.
Published: (2026)

Time-Efficient Evaluation and Enhancement of Adversarial Robustness in Deep Neural Networks
by: Lin, Runqi
Published: (2025)

Catastrophic Overfitting: A Potential Blessing in Disguise
by: Zhao, Mengnan, et al.
Published: (2024)

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

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
by: Mallinar, Neil, et al.
Published: (2022)

Understanding and Enhancing the Transferability of Jailbreaking Attacks
by: Lin, Runqi, et al.
Published: (2025)

Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
by: Li, Jiping, et al.
Published: (2025)

Robust Training of Federated Models with Extremely Label Deficiency
by: Zhang, Yonggang, et al.
Published: (2024)

Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models
by: Zhang, Yiyang, et al.
Published: (2026)

Overfitting in Adaptive Robust Optimization
by: Zhu, Karl, et al.
Published: (2025)

Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
by: Yuan, Suqin, et al.
Published: (2025)

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

Benign Overfitting in Time Series Linear Models with Over-Parameterization
by: Nakakita, Shogo, et al.
Published: (2022)

Generative Model Inversion Through the Lens of the Manifold Hypothesis
by: Peng, Xiong, et al.
Published: (2025)

BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
by: Zhang, Jingfeng, et al.
Published: (2023)

MeGU: Machine-Guided Unlearning with Target Feature Disentanglement
by: Wang, Haoyu, et al.
Published: (2026)

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

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

Logarithmic Width Suffices for Robust Memorization
by: Egosi, Amitsour, et al.
Published: (2025)

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)

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
by: Fu, Shaopeng, et al.
Published: (2023)

Testing for Overfitting
by: Schmidt, James
Published: (2023)

What If the Input is Expanded in OOD Detection?
by: Zhang, Boxuan, et al.
Published: (2024)

2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency
by: Fu, Yonggan, et al.
Published: (2021)

Robust Policy Optimization to Prevent Catastrophic Forgetting
by: Sabbaghi, Mahdi, et al.
Published: (2026)

Residual Stream Analysis of Overfitting And Structural Disruptions
by: Liu, Quan, et al.
Published: (2026)

Relative Overfitting and Accept-Reject Framework
by: Liu, Yanxin, et al.
Published: (2025)

MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCIL
by: Pang, Jinhui, et al.
Published: (2025)

Adjusted Overfitting Regression
by: Wilson, Dylan
Published: (2024)

Overfitting In Contrastive Learning?
by: Rabin, Zachary, et al.
Published: (2024)

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
by: Cao, Chentao, et al.
Published: (2024)

Fine-Grained Gradient Restriction: A Simple Approach for Mitigating Catastrophic Forgetting
by: Liu, Bo, et al.
Published: (2024)

Rethinking Deep Research from the Perspective of Web Content Distribution Matching
by: Yu, Zixuan, et al.
Published: (2026)

Mitigating Label Noise on Graph via Topological Sample Selection
by: Wu, Yuhao, et al.
Published: (2024)

Model Inversion Attacks: A Survey of Approaches and Countermeasures
by: Zhou, Zhanke, et al.
Published: (2024)