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 481–490 of 523 papers

TitleStatusHype
Backdoor Attack and Defense for Deep Regression—0
Excess Capacity and Backdoor PoisoningCode0
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers—0
Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting—0
BadNL: Backdoor Attacks Against NLP Models—0
Handcrafted Backdoors in Deep Neural Networks—0
Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations—0
Poisoning MorphNet for Clean-Label Backdoor Attack to Point Clouds—0
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning—0
A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verification—0
Show:102550
← PrevPage 49 of 53Next →

No leaderboard results yet.