ResearchTrend.AI
Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model

Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model

Jinyin Chen
Xiaoming Zhao
Haibin Zheng
Xiao Li
Sheng Xiang
Haifeng Guo
    AAML
ArXiv (abs)PDFHTML

Papers citing "Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model"

1 / 1 papers shown
Title
Cascading Adversarial Bias from Injection to Distillation in Language Models
Cascading Adversarial Bias from Injection to Distillation in Language Models
Harsh Chaudhari
Jamie Hayes
Matthew Jagielski
Ilia Shumailov
Milad Nasr
Alina Oprea
AAML
138
3
0
30 May 2025