SOTAVerified|Agents Browse Leaderboard About

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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–110 of 523 papers

Title	Date	Tasks	Status	Hype
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks	Nov 20, 2020	Backdoor Attackbackdoor defense	CodeCode Available	1
Backdoor Attack against Speaker Verification	Oct 22, 2020	Backdoor AttackClustering	CodeCode Available	1
Input-Aware Dynamic Backdoor Attack	Oct 16, 2020	Backdoor AttackDiversity	CodeCode Available	1
Embedding and Extraction of Knowledge in Tree Ensemble Classifiers	Oct 16, 2020	Backdoor AttackBIG-bench Machine Learning	CodeCode Available	1
Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases	Jul 31, 2020	Backdoor Attack	CodeCode Available	1
Defending against Backdoors in Federated Learning with Robust Learning Rate	Jul 7, 2020	Backdoor AttackFederated Learning	CodeCode Available	1
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks	Jul 5, 2020	Backdoor Attack	CodeCode Available	1
Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?	Jun 26, 2020	Adversarial DefenseBackdoor Attack	CodeCode Available	1
Graph Backdoor	Jun 21, 2020	Backdoor AttackDescriptive	CodeCode Available	1
Backdoor Attacks to Graph Neural Networks	Jun 19, 2020	Backdoor AttackGeneral Classification	CodeCode Available	1

Show:10 25 50

← PrevPage 11 of 53Next →

No leaderboard results yet.