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 281–290 of 523 papers

TitleStatusHype
Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks—0
The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers—0
The last Dance : Robust backdoor attack via diffusion models and bayesian approach—0
The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright Breaches Without Adjusting Finetuning Pipeline—0
Towards Robust Physical-world Backdoor Attacks on Lane Detection—0
Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger—0
Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimization—0
Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning—0
Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approach—0
Transferable Graph Backdoor Attack—0
Show:102550
← PrevPage 29 of 53Next →

No leaderboard results yet.