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 171–180 of 523 papers

TitleStatusHype
A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning—0
Backdoor Attack with Mode Mixture Latent Modification—0
Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning—0
AS-FIBA: Adaptive Selective Frequency-Injection for Backdoor Attack on Deep Face Restoration—0
Defending against Backdoor Attacks in Natural Language Generation—0
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee—0
Contributor-Aware Defenses Against Adversarial Backdoor Attacks—0
CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks—0
DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning—0
Backdoor Attack with Imperceptible Input and Latent Modification—0
Show:102550
← PrevPage 18 of 53Next →

No leaderboard results yet.