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 411–420 of 523 papers

TitleStatusHype
ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger—0
Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain—0
Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving—0
CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks—0
CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction—0
Compression-Resistant Backdoor Attack against Deep Neural Networks—0
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning—0
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer—0
Contributor-Aware Defenses Against Adversarial Backdoor Attacks—0
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee—0
Show:102550
← PrevPage 42 of 53Next →

No leaderboard results yet.