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 301–310 of 523 papers

TitleStatusHype
Multi-Target Federated Backdoor Attack Based on Feature Aggregation—0
Natural Backdoor Attack on Text Data—0
Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving—0
Neighboring Backdoor Attacks on Graph Convolutional Network—0
NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations—0
Object-oriented backdoor attack against image captioning—0
On Certifying Robustness against Backdoor Attacks via Randomized Smoothing—0
On Feasibility of Server-side Backdoor Attacks on Split Learning—0
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models—0
PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning—0
Show:102550
← PrevPage 31 of 53Next →

No leaderboard results yet.