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 71–80 of 523 papers

TitleStatusHype
Data Free Backdoor AttacksCode0
An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers—0
Backdooring Outlier Detection Methods: A Novel Attack Approach—0
Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer—0
LaserGuider: A Laser Based Physical Backdoor Attack against Deep Neural Networks—0
PBP: Post-training Backdoor Purification for Malware ClassifiersCode0
Behavior Backdoor for Deep Learning Models—0
Streamlined Federated Unlearning: Unite as One to Be Highly Efficient—0
LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm—0
BadScan: An Architectural Backdoor Attack on Visual State Space Models—0
Show:102550
← PrevPage 8 of 53Next →

No leaderboard results yet.