all AI news
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
April 15, 2024, 4:42 a.m. | Runqi Lin, Chaojian Yu, Tongliang Liu
cs.LG updates on arXiv.org arxiv.org
Abstract: Single-step adversarial training (SSAT) has demonstrated the potential to achieve both efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a phenomenon that leads to a severely distorted classifier, making it vulnerable to multi-step adversarial attacks. In this work, we observe that some adversarial examples generated on the SSAT-trained network exhibit anomalous behaviour, that is, although these training samples are generated by the inner maximization process, their associated loss decreases instead, which we named …
abstract adversarial adversarial attacks adversarial examples adversarial training arxiv attacks classifier cs.lg efficiency examples generated however leads making observe overfitting regularization robustness training type via vulnerable work
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
#13721 - Data Engineer - AI Model Testing
@ Qualitest | Miami, Florida, United States
Elasticsearch Administrator
@ ManTech | 201BF - Customer Site, Chantilly, VA