CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models

2 September 2024

Yuwen Pu

Xuhong Zhang

Tianyu Du

Shouling Ji

Papers citing "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"

3 / 3 papers shown

Title
MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic Hang Wang Zhen Xiang David J. Miller G. Kesidis AAML 25 40 0 13 May 2022
Model-Reuse Attacks on Deep Learning Systems Yujie Ji Xinyang Zhang S. Ji Xiapu Luo Ting Wang SILM AAML 123 186 0 02 Dec 2018
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 273 2,878 0 15 Sep 2016