SOTAVerified

Backdoor Attack

Backdoor attacks inject maliciously constructed data into a training set so that, at test time, the trained model misclassifies inputs patched with a backdoor trigger as an adversarially-desired target class.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 311–320 of 523 papers

TitleStatusHype
Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models—0
Partial train and isolate, mitigate backdoor attack—0
PBSM: Backdoor attack against Keyword spotting based on pitch boosting and sound masking—0
Physical Invisible Backdoor Based on Camera Imaging—0
PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks—0
PointBA: Towards Backdoor Attacks in 3D Point Cloud—0
Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers—0
Poisoning MorphNet for Clean-Label Backdoor Attack to Point Clouds—0
Poison in the Well: Feature Embedding Disruption in Backdoor Attacks—0
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models—0
Show:102550
← PrevPage 32 of 53Next →

No leaderboard results yet.