Codes for this paper Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets NeurIPS 2022
Code of Data-Limited TrojanNet Detector (DL-TND) and Data-Free TrojanNet Detector (DF-TND) from the paper: Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
Backdoor attack is an important type of adversarial attack against deep neural network (DNN) classifiers. A classifier being attacked will predict to the attacker's target class when a test sample is embedded with a backdoor pattern/trigger. Backdoor defenses can be deployed post-training, where…