Robustness Improvement Method

Certified Distributional Robustness on Smoothed Classifiers

Authors: Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang | Published: 2020-10-21 | Updated: 2021-04-30
Dataset evaluation
Robustness Improvement Method
Adversarial Example

Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples

Authors: Sven Gowal, Chongli Qin, Jonathan Uesato, Timothy Mann, Pushmeet Kohli | Published: 2020-10-07 | Updated: 2021-03-30
Poisoning
Robustness Improvement Method
Adversarial attack

Constraining Logits by Bounded Function for Adversarial Robustness

Authors: Sekitoshi Kanai, Masanori Yamada, Shin'ya Yamaguchi, Hiroshi Takahashi, Yasutoshi Ida | Published: 2020-10-06
Robustness Improvement Method
Improvement of Learning
Adversarial attack

Adversarial Boot Camp: label free certified robustness in one epoch

Authors: Ryan Campbell, Chris Finlay, Adam M Oberman | Published: 2020-10-05
Robustness Improvement Method
Improvement of Learning
Adversarial attack

Bag of Tricks for Adversarial Training

Authors: Tianyu Pang, Xiao Yang, Yinpeng Dong, Hang Su, Jun Zhu | Published: 2020-10-01 | Updated: 2021-03-31
Model Architecture
Robustness Improvement Method
Optimization Methods

Erratum Concerning the Obfuscated Gradients Attack on Stochastic Activation Pruning

Authors: Guneet S. Dhillon, Nicholas Carlini | Published: 2020-09-30
Watermarking
Robustness Improvement Method
Attack Evaluation

DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

Authors: Huanrui Yang, Jingyang Zhang, Hongliang Dong, Nathan Inkawhich, Andrew Gardner, Andrew Touchet, Wesley Wilkes, Heath Berry, Hai Li | Published: 2020-09-30 | Updated: 2020-10-18
Robustness Improvement Method
Adversarial Example
Vulnerability Assessment Method

Evaluating Ensemble Robustness Against Adversarial Attacks

Authors: George Adam, Romain Speciel | Published: 2020-05-12
Robustness Improvement Method
Promotion of Diversity
Adversarial Example

Robustness Verification for Classifier Ensembles

Authors: Dennis Gross, Nils Jansen, Guillermo A. Pérez, Stephan Raaijmakers | Published: 2020-05-12 | Updated: 2020-07-09
Robustness Improvement Method
Attack Detection
Deep Learning

Provable Robust Classification via Learned Smoothed Densities

Authors: Saeed Saremi, Rupesh Srivastava | Published: 2020-05-09
Bayesian Classification
Poisoning
Robustness Improvement Method