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 351–360 of 523 papers

TitleStatusHype
Backdoor Attacks for Remote Sensing Data with Wavelet TransformCode1
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive LearningCode1
MSDT: Masked Language Model Scoring Defense in Text DomainCode0
Going In Style: Audio Backdoors Through Stylistic TransformationsCode0
Untargeted Backdoor Attack against Object DetectionCode1
BATT: Backdoor Attack with Transformation-based Triggers—0
Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via MotifsCode0
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated LearningCode1
Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning—0
Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis—0
Show:102550
← PrevPage 36 of 53Next →

No leaderboard results yet.