DeepAI AI Chat
Log In Sign Up

Can collaborative learning be private, robust and scalable?

by   Dmitrii Usynin, et al.

We investigate the effectiveness of combining differential privacy, model compression and adversarial training to improve the robustness of models against adversarial samples in train- and inference-time attacks. We explore the applications of these techniques as well as their combinations to determine which method performs best, without a significant utility trade-off. Our investigation provides a practical overview of various methods that allow one to achieve a competitive model performance, a significant reduction in model's size and an improved empirical adversarial robustness without a severe performance degradation.


page 3

page 6


Mutual Adversarial Training: Learning together is better than going alone

Recent studies have shown that robustness to adversarial attacks can be ...

Robustness, Privacy, and Generalization of Adversarial Training

Adversarial training can considerably robustify deep neural networks to ...

Federated Learning in Adversarial Settings

Federated Learning enables entities to collaboratively learn a shared pr...

Adversarially Trained Model Compression: When Robustness Meets Efficiency

The robustness of deep models to adversarial attacks has gained signific...

Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks

Adversarial training has been proven to be an effective technique for im...

Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning

Adversarial training (i.e., training on adversarially perturbed input da...

A Study on FGSM Adversarial Training for Neural Retrieval

Neural retrieval models have acquired significant effectiveness gains ov...