CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Verifying robustness of neural network classifiers has attracted great interests and attention due to the success of deep neural networks and their unexpected vulnerability to adversarial perturbations. Although finding minimum adversarial distortion of neural networks (with ReLU activations) has be...
Main Authors: | Boopathy, Akhilan, Weng, Tsui-Wei, Chen, Pin-Yu, Liu, Sijia, 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)
2021
|
Online Access: | https://hdl.handle.net/1721.1/129951 |
Similar Items
-
Fast Training of Provably Robust Neural Networks by SingleProp
by: Boopathy, Akhilan, et al.
Published: (2022) -
Towards verifying robustness of neural networks against a family of semantic perturbations
by: Mohapatra, Jeet, et al.
Published: (2021) -
Efficient Neural Network Robustness Certification with General Activation Functions
by: Zhang, Huan, et al.
Published: (2021) -
Towards More Generalizable Neural Networks via Modularity
by: Boopathy, Akhilan
Published: (2022) -
Low power convolutional neural network (CNN)
by: Lim, Wu Cong
Published: (2019)