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
Manipulating and Mitigating Generative Model Biases without Retraining—0
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models—0
A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks—0
Towards Adversarial Robustness And Backdoor Mitigation in SSLCode0
Impart: An Imperceptible and Effective Label-Specific Backdoor Attack—0
Invisible Backdoor Attack Through Singular Value Decomposition—0
Backdoor Attack with Mode Mixture Latent Modification—0
AS-FIBA: Adaptive Selective Frequency-Injection for Backdoor Attack on Deep Face Restoration—0
Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression—0
iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself—0
Show:102550
← PrevPage 29 of 53Next →

No leaderboard results yet.