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 241–250 of 523 papers

TitleStatusHype
EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry—0
Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion—0
A4O: All Trigger for One sample—0
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering—0
Feature Grinding: Efficient Backdoor Sanitation in Deep Neural Networks—0
CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks—0
Backdoor Attacks on the DNN Interpretation System—0
Federated Learning with Flexible Architectures—0
A Robust Attack: Displacement Backdoor Attack—0
Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving—0
Show:102550
← PrevPage 25 of 53Next →

No leaderboard results yet.