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 371–380 of 523 papers

TitleStatusHype
Backdoor Detection through Replicated Execution of Outsourced Training—0
Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models—0
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers—0
Backdooring Convolutional Neural Networks via Targeted Weight Perturbations—0
Backdooring Outlier Detection Methods: A Novel Attack Approach—0
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing—0
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning—0
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers—0
Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire—0
BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models—0
Show:102550
← PrevPage 38 of 53Next →

No leaderboard results yet.