Source code and models for "Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks"
The main features of thunlp/neuba are: Transfer Learning Security.
Open-source alternatives to thunlp/neuba include: neulab/ripple — This repository contains the code to implement experiments from the paper "Weight Poisoning Attacks on Pre-trained… umbcvision/hidden-trigger-backdoor-attacks — Official Implementation of the AAAI-20 paper [Hidden Trigger Backdoor Attacks][paper].
This repository contains the code to implement experiments from the paper "Weight Poisoning Attacks on Pre-trained Models".
Official Implementation of the AAAI-20 paper Hidden Trigger Backdoor Attackspaper