Defenses

Supported Defenses

The following table lists the supported defenses in BackdoorMBTI:

Defense	Modality	Input	Stage	Output	Paper
STRIP	Audio, Image, and text	backdoor model, clean dataset	post-training	clean dataset	STRIP: A Defence Against Trojan Attacks on Deep Neural Networks
AC	Audio, Image, and text	backdoor model, clean dataset, poison dataset	post-training	clean model, clean dataset	Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
FT	Audio, Image, and text	backdoor model, clean dataset	in-training	clean model	Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
FP	Audio, Image, and text	backdoor model, clean dataset	post-training	clean model	Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
ABL	Audio, Image, and text	backdoor model, poison dataset	in-training	clean model	Anti-Backdoor Learning: Training Clean Models on Poisoned Data
CLP	Audio, Image, and text	backdoor model	post-training	clean model	Data-free Backdoor Removal based on Channel Lipschitzness
NC	Image	backdoor model, clean dataset	post-training	clean model, trigger pattern	Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
MNTD	Image	backdoor model	post-training	detection result	Detecting AI Trojans Using Meta Neural Analysis
FreeEagle	Image	backdoor model	post-training	detection result	FREEEAGLE: Detecting Complex Neural Trojans in Data-Free Cases