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 251–260 of 523 papers

TitleStatusHype
A Robust Attack: Displacement Backdoor Attack—0
FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition—0
Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving—0
Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain—0
Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark—0
Adversarial Targeted Forgetting in Regularization and Generative Based Continual Learning Models—0
Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving—0
ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger—0
CBPF: Filtering Poisoned Data Based on Composite Backdoor Attack—0
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks—0
Show:102550
← PrevPage 26 of 53Next →

No leaderboard results yet.