Towards Certificated Model Robustness Against Weight Perturbations

Towards Certificated Model Robustness Against Weight Perturbations

<jats:p>This work studies the sensitivity of neural networks to weight perturbations, firstly corresponding to a newly developed threat model that perturbs the neural network parameters. We propose an efficient approach to compute a certified robustness bound of weight perturbations, within wh...

Full description

Bibliographic Details
Main Authors: Weng, Tsui-Wei, Zhao, Pu, Liu, Sijia, Chen, Pin-Yu, Lin, Xue, Daniel, Luca
Other Authors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Format: Article
Language:English
Published: Association for the Advancement of Artificial Intelligence (AAAI) 2022
Online Access:https://hdl.handle.net/1721.1/143107

Internet

https://hdl.handle.net/1721.1/143107

Similar Items