← Search

Nodens Koren

3 accepted papers

2023

Reconstructive Neuron Pruning for Backdoor Defense

ICML 2023poster

Deep neural networks (DNNs) have been found to be vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. While existing defense methods have demonstrated promising results, it is still not clear how to effectively remove backdoor-associated…

2021

Anti-Backdoor Learning: Training Clean Models on Poisoned Data

NeurIPS 2021poster

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training methods can be devised to prevent the backdoor triggers being inj…

2021

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

ICLR 2021poster

Deep neural networks (DNNs) are known vulnerable to backdoor attacks, a training time attack that injects a trigger pattern into a small proportion of training data so as to control the model's prediction at the test time. Backdoor attacks are notably dangerous since they do not affect the model's p…