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 141–150 of 523 papers

TitleStatusHype
Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks—0
Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire—0
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers—0
BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models—0
BAAAN: Backdoor Attacks Against Auto-encoder and GAN-Based Machine Learning Models—0
A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verification—0
Compression-Resistant Backdoor Attack against Deep Neural Networks—0
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning—0
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning—0
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing—0
Show:102550
← PrevPage 15 of 53Next →

No leaderboard results yet.