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 201–210 of 523 papers

TitleStatusHype
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning—0
Defending Backdoor Attacks on Vision Transformer via Patch Processing—0
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System—0
Defending Backdoor Data Poisoning Attacks by Using Noisy Label Defense Algorithm—0
Defending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning—0
Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models—0
A semantic backdoor attack against Graph Convolutional Networks—0
Compression-Resistant Backdoor Attack against Deep Neural Networks—0
Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations—0
A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks—0
Show:102550
← PrevPage 21 of 53Next →

No leaderboard results yet.