Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised Defense

Availability poisons exploit supervised learning (SL) algorithms by introducing class-related shortcut features in images such that models trained on poisoned data are useless for real-world datasets. Self-supervised learning (SSL), which utilizes augmentations to learn instance discrimination, is r...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-09
Hauptverfasser:	Styborski, Jeremy, Lyu, Mingzhi, Huang, Yi, Adams, Kong
Format:	Artikel
Sprache:	eng
Schlagworte:	Ablation Algorithms Availability Datasets Machine learning Poisoning Poisons Robustness Self-supervised learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!