A survey of backdoor attacks and defences: From deep neural networks to large language models

Deep neural networks (DNNs) have found extensive applications in safety-critical artificial intelligence systems, such as autonomous driving and facial recognition systems. However, recent research has revealed their susceptibility to backdoors maliciously injected by adversaries. This vulnerability...

Description complète

Détails bibliographiques

Auteurs principaux:	Ling-Xin Jin, Wei Jiang, Xiang-Yu Wen, Mei-Yu Lin, Jin-Yu Zhan, Xing-Zhi Zhou, Maregu Assefa Habtie, Naoufel Werghi
Format:	Artigo
Langue:	Inglês
Publié:	KeAi Communications Co., Ltd. 2025-09-01
Collection:	Journal of Electronic Science and Technology
Sujets:	Backdoor attacks Backdoor defenses Deep neural networks Large language model
Accès en ligne:	http://www.sciencedirect.com/science/article/pii/S1674862X25000278
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!