Double landmines: invisible textual backdoor attacks based on dual-trigger

Abstract Backdoor attacks pose an important security threat to textual large language models. Exploring textual backdoor attacks not only helps reveal the potential security risks of models, but also promotes innovation and development of defense mechanisms. Currently, most textual backdoor attack m...

Descripció completa

Dades bibliogràfiques

Autors principals:	Yang Hou, Qiuling Yue, Lujia Chai, Guozhao Liao, Wenbao Han, Wei Ou
Format:	Artigo
Idioma:	Inglês
Publicat:	SpringerOpen 2025-12-01
Col·lecció:	Cybersecurity
Matèries:	Textual backdoor attack Dual-trigger Abstract text features
Accés en línia:	https://doi.org/10.1186/s42400-025-00512-z
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!