Cover Image

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Mengnan, Zhang, Lihe, Zheng, Tianhang, Wang, Bo, Yin, Baocai
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Mitigating Error Amplification in Fast Adversarial Training
by: Zhao, Mengnan, et al.
Published: (2026)

AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors
by: Zhao, Mengnan, et al.
Published: (2024)

FedReview: A Review Mechanism for Rejecting Poisoned Updates in Federated Learning
by: Zheng, Tianhang, et al.
Published: (2024)

CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models
by: Zhao, Mengnan, et al.
Published: (2026)

Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
by: Wang, Bo, et al.
Published: (2026)

Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
by: Beerens, Lucas, et al.
Published: (2025)

Fast and Lightweight Backdoor Detection via Head Random Probing
by: Yu, Yinbo, et al.
Published: (2026)

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
by: Pal, Soumyadeep, et al.
Published: (2024)

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

Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
by: Kong, Cong, et al.
Published: (2024)

Backdoor Detection through Replicated Execution of Outsourced Training
by: Jia, Hengrui, et al.
Published: (2025)

LoBAM: LoRA-Based Backdoor Attack on Model Merging
by: Yin, Ming, et al.
Published: (2024)

Information Theoretic Adversarial Training of Large Language Models
by: Zhang, Yiwei, et al.
Published: (2026)

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
by: Nguyen, Quang Duc, et al.
Published: (2026)

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training
by: Zhang, Yuxiang, et al.
Published: (2024)

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning
by: Vyas, Sanyam, et al.
Published: (2025)

Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses
by: Pawlak, Stanisław, et al.
Published: (2025)

How Catastrophic is Your LLM? Certifying Risk in Conversation
by: Wang, Chengxiao, et al.
Published: (2025)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
by: Chen, Zhuowei, et al.
Published: (2025)

Backdoor Graph Condensation
by: Wu, Jiahao, et al.
Published: (2024)

Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
by: Shin, Jeongjin, et al.
Published: (2024)

Compromising Embodied Agents with Contextual Backdoor Attacks
by: Liu, Aishan, et al.
Published: (2024)

Generating Adversarial Point Clouds Using Diffusion Model
by: Zhao, Ruiyang, et al.
Published: (2025)

Backdoor defense, learnability and obfuscation
by: Christiano, Paul, et al.
Published: (2024)

How to Backdoor the Knowledge Distillation
by: Wu, Chen, et al.
Published: (2025)

Heterogeneous Graph Backdoor Attack
by: Chen, Jiawei, et al.
Published: (2025)

Defending Against Unforeseen Failure Modes with Latent Adversarial Training
by: Casper, Stephen, et al.
Published: (2024)

Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications
by: Zhang, Lu, et al.
Published: (2025)

Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
by: Min, Rui, et al.
Published: (2024)

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
by: Wang, Yifei, et al.
Published: (2026)

Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
by: Chen, Xiangxiang, et al.
Published: (2025)

Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain
by: Huang, Yuanmin, et al.
Published: (2025)

NPAT Null-Space Projected Adversarial Training Towards Zero Deterioration
by: Hu, Hanyi, et al.
Published: (2024)

Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders
by: Han, Tingxu, et al.
Published: (2024)

BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems
by: Fang, Jing, et al.
Published: (2025)

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
by: An, Shengwei, et al.
Published: (2023)

Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training
by: Yi, Bongsoo, et al.
Published: (2024)

Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
by: Wang, Yisen, et al.
Published: (2025)

Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective
by: Li, Nan, et al.
Published: (2024)