Effective defense against physically embedded backdoor attacks via clustering-based filtering

Abstract Backdoor attacks pose a severe threat to the integrity of machine learning models, especially in real-world image classification tasks. In such attacks, adversaries embed malicious behaviors triggered by specific patterns in the training data, causing models to misclassify whenever the trig...

詳細記述

書誌詳細

出版年:	Complex & Intelligent Systems
第一著者:	Mohammed Kutbi
フォーマット:	論文
言語:	英語
出版事項:	Springer 2025-04-01
主題:	Machine learning security Backdoor attacks Data poisoning Deep learning
オンライン･アクセス:	https://doi.org/10.1007/s40747-025-01876-y