Certified Robustness

Where Classification Fails, Interpretation Rises

Authors: Chanh Nguyen, Georgi Georgiev, Yujie Ji, Ting Wang | Published: 2017-12-02
FDI Attack Detection Methods
Certified Robustness
Adversarial Learning

Evaluating Robustness of Neural Networks with Mixed Integer Programming

Authors: Vincent Tjeng, Kai Xiao, Russ Tedrake | Published: 2017-11-20 | Updated: 2019-02-18
Certified Robustness
Robustness
Deep Learning Technology

The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels

Authors: Yannic Kilcher, Thomas Hofmann | Published: 2017-11-15
Backdoor Detection
Proactive Defense
Certified Robustness

LatentPoison – Adversarial Attacks On The Latent Space

Authors: Antonia Creswell, Anil A. Bharath, Biswa Sengupta | Published: 2017-11-08
Poisoning
Certified Robustness
Adversarial attack

Provable defenses against adversarial examples via the convex outer adversarial polytope

Authors: Eric Wong, J. Zico Kolter | Published: 2017-11-02 | Updated: 2018-06-08
Certified Robustness
Robustness
Deep Learning Technology

Attacking Binarized Neural Networks

Authors: Angus Galloway, Graham W. Taylor, Medhat Moussa | Published: 2017-11-01 | Updated: 2018-01-31
Certified Robustness
Robustness Improvement Method
Adversarial Example

Attacking the Madry Defense Model with $L_1$-based Adversarial Examples

Authors: Yash Sharma, Pin-Yu Chen | Published: 2017-10-30 | Updated: 2018-07-27
Certified Robustness
Robustness Improvement Method
Adversarial Example Detection

Boosting Adversarial Attacks with Momentum

Authors: Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su, Jun Zhu, Xiaolin Hu, Jianguo Li | Published: 2017-10-17 | Updated: 2018-03-22
Certified Robustness
Robustness Improvement Method
Adversarial Example Detection

Bayesian Hypernetworks

Authors: David Krueger, Chin-Wei Huang, Riashat Islam, Ryan Turner, Alexandre Lacoste, Aaron Courville | Published: 2017-10-13 | Updated: 2018-04-24
Certified Robustness
Model Design
Label

Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification

Authors: Xiaoyu Cao, Neil Zhenqiang Gong | Published: 2017-09-17 | Updated: 2019-12-31
Certified Robustness
Adversarial Learning
Adversarial Example Detection