Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack

The vulnerabilities to backdoor attacks have recently threatened the trustworthiness of machine learning models in practical applications. Conventional wisdom suggests that not everyone can be an attacker since the process of designing the trigger generation algorithm often involves significant effo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-09
Hauptverfasser:	Sze Jue Yang, Nguyen, Quang, Chan, Chee Seng, Doan, Khoa D
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Image compression Machine learning Poisoning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!