computer-vision-7
Backdoor Attack
3260 papers • 126 benchmarks • 313 datasets
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.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in backdoor-attack-22
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find backdoor-attack-22 models and implementations
3 papers 44
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Hidden Trigger Backdoor Attacks
Aniruddha Saha, H. Pirsiavash, Akshayvarun Subramanya•Sun Sep 29 2019
This work proposes a novel form of backdoor attack where poisoned data look natural with correct labels and also more importantly, the attacker hides the trigger in the poisoned data and keeps the trigger secret until the test time.
707