Cover Image

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zhaoxin, Wang, Handing, Tian, Cong, Jin, Yaochu
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

Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models
by: Liu, Jiangtao, et al.
Published: (2025)

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

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models
by: Wang, Zhaoxin, et al.
Published: (2025)

Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
by: Wang, Zhaoxin, et al.
Published: (2025)

Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective
by: Gui, Jie, et al.
Published: (2024)

DTVI: Dual-Stage Textual and Visual Intervention for Safe Text-to-Image Generation
by: Tan, Binhong, et al.
Published: (2026)

Preventing Catastrophic Forgetting through Memory Networks in Continuous Detection
by: Bhatt, Gaurav, et al.
Published: (2024)

BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM
by: Zhang, Li, et al.
Published: (2024)

When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models
by: Yan, Yuping, et al.
Published: (2025)

A Generic Self-Supervised Framework of Learning Invariant Discriminative Features
by: Ntelemis, Foivos, et al.
Published: (2022)

FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods
by: Pan, Chao, et al.
Published: (2026)

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

From Parameter to Representation: A Closed-Form Approach for Controllable Model Merging
by: Wu, Jialin, et al.
Published: (2025)

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

Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
by: Jiang, Jiarui, et al.
Published: (2024)

Revisiting Min-Max Optimization Problem in Adversarial Training
by: Ahmadi, Sina Hajer, et al.
Published: (2024)

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

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

Adversarial Training against Location-Optimized Adversarial Patches
by: Rao, Sukrut, et al.
Published: (2020)

Fast Learnings of Coupled Nonnegative Tensor Decomposition Using Optimal Gradient and Low-rank Approximation
by: Wang, Xiulin, et al.
Published: (2023)

OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection
by: Fernández-Hernández, Alberto, et al.
Published: (2025)

FastCLIP: A Suite of Optimization Techniques to Accelerate CLIP Training with Limited Resources
by: Wei, Xiyuan, et al.
Published: (2024)

SORA: Free Second-Order Attacks in Fast Adversarial Training
by: Teymourian, Mazdak, et al.
Published: (2026)

TRIX- Trading Adversarial Fairness via Mixed Adversarial Training
by: Medi, Tejaswini, et al.
Published: (2025)

Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation
by: Mi, Xiaoyue, et al.
Published: (2023)

EXACFS -- A CIL Method to mitigate Catastrophic Forgetting
by: Balasubramanian, S, et al.
Published: (2024)

Improving Adversarial Energy-Based Model via Diffusion Process
by: Geng, Cong, et al.
Published: (2024)

ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learning
by: Ye, Zihan, et al.
Published: (2024)

What is Adversarial Training for Diffusion Models?
by: Rosaria, Briglia Maria, et al.
Published: (2025)

GReAT: A Graph Regularized Adversarial Training Method
by: Bayram, Samet, et al.
Published: (2023)

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget
by: Fakorede, Olukorede, et al.
Published: (2024)

Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models
by: Shen, Shufan, et al.
Published: (2025)

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

Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval
by: Yuan, Xu, et al.
Published: (2023)

Contrastive Adversarial Training for Unsupervised Domain Adaptation
by: Chen, Jiahong, et al.
Published: (2024)

Do Counterfactual Examples Complicate Adversarial Training?
by: Yeats, Eric, et al.
Published: (2024)

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

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

Adversarial Training in Low-Label Regimes with Margin-Based Interpolation
by: Ye, Tian, et al.
Published: (2024)

Perturbing the Gradient for Alleviating Meta Overfitting
by: Gogoi, Manas, et al.
Published: (2024)