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 501–523 of 523 papers

TitleStatusHype
CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks—0
HaS-Nets: A Heal and Select Mechanism to Defend DNNs Against Backdoor Attacks for Data Collection Scenarios—0
DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation—0
Backdoor Attacks on the DNN Interpretation System—0
EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks—0
Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks—0
BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models—0
Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems—0
Deep Learning Backdoors—0
Natural Backdoor Attack on Text Data—0
BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements—0
Adversarial examples are useful too!Code0
Rethinking the Trigger of Backdoor Attack—0
Dynamic Backdoor Attacks Against Machine Learning Models—0
On Certifying Robustness against Backdoor Attacks via Randomized Smoothing—0
Defending against Backdoor Attack on Deep Neural Networks—0
Targeted Forgetting and False Memory Formation in Continual Learners through Adversarial Backdoor Attacks—0
NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations—0
Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy—0
Defending Neural Backdoors via Generative Distribution ModelingCode0
Regula Sub-rosa: Latent Backdoor Attacks on Deep Neural Networks—0
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural NetworksCode0
Backdooring Convolutional Neural Networks via Targeted Weight Perturbations—0
Show:102550
← PrevPage 11 of 11Next →

No leaderboard results yet.