Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Tsui-Wei Weng

Tsui-Wei Weng

On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning


Feb 20, 2021
Ren Wang, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Chuang Gan, Meng Wang

Figure 1 for On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Figure 2 for On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Figure 3 for On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Figure 4 for On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning

  Access Paper or Ask Questions

Fast Training of Provably Robust Neural Networks by SingleProp


Feb 01, 2021
Akhilan Boopathy, Tsui-Wei Weng, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Luca Daniel

Figure 1 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 2 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 3 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 4 for Fast Training of Provably Robust Neural Networks by SingleProp
* Published at AAAI 2021 
  Access Paper or Ask Questions

Higher-Order Certification for Randomized Smoothing


Oct 13, 2020
Jeet Mohapatra, Ching-Yun Ko, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel

Figure 1 for Higher-Order Certification for Randomized Smoothing
Figure 2 for Higher-Order Certification for Randomized Smoothing
Figure 3 for Higher-Order Certification for Randomized Smoothing
Figure 4 for Higher-Order Certification for Randomized Smoothing
* Accepted to NeurIPS2020(spotlight) 
  Access Paper or Ask Questions

Robust Deep Reinforcement Learning through Adversarial Loss


Aug 05, 2020
Tuomas Oikarinen, Tsui-Wei Weng, Luca Daniel

Figure 1 for Robust Deep Reinforcement Learning through Adversarial Loss
Figure 2 for Robust Deep Reinforcement Learning through Adversarial Loss
Figure 3 for Robust Deep Reinforcement Learning through Adversarial Loss
Figure 4 for Robust Deep Reinforcement Learning through Adversarial Loss

  Access Paper or Ask Questions

Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation


Aug 18, 2019
Yuh-Shyang Wang, Tsui-Wei Weng, Luca Daniel

Figure 1 for Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation
Figure 2 for Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation
Figure 3 for Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation
Figure 4 for Verification of Neural Network Control Policy Under Persistent Adversarial Perturbation

  Access Paper or Ask Questions

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective


Jun 10, 2019
Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin

Figure 1 for Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Figure 2 for Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Figure 3 for Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
Figure 4 for Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
* Accepted by IJCAI 2019, the 28th International Joint Conference on Artificial Intelligence 
  Access Paper or Ask Questions

POPQORN: Quantifying Robustness of Recurrent Neural Networks


May 17, 2019
Ching-Yun Ko, Zhaoyang Lyu, Tsui-Wei Weng, Luca Daniel, Ngai Wong, Dahua Lin

Figure 1 for POPQORN: Quantifying Robustness of Recurrent Neural Networks
Figure 2 for POPQORN: Quantifying Robustness of Recurrent Neural Networks
Figure 3 for POPQORN: Quantifying Robustness of Recurrent Neural Networks
Figure 4 for POPQORN: Quantifying Robustness of Recurrent Neural Networks
* 10 pages, Ching-Yun Ko and Zhaoyang Lyu contributed equally, accepted to ICML 2019. Please see arXiv source codes for the appendix by clicking [Other formats] 
  Access Paper or Ask Questions

Optimal Finite-Sum Smooth Non-Convex Optimization with SARAH


Jan 22, 2019
Lam M. Nguyen, Marten van Dijk, Dzung T. Phan, Phuong Ha Nguyen, Tsui-Wei Weng, Jayant R. Kalagnanam

Figure 1 for Optimal Finite-Sum Smooth Non-Convex Optimization with SARAH
Figure 2 for Optimal Finite-Sum Smooth Non-Convex Optimization with SARAH
Figure 3 for Optimal Finite-Sum Smooth Non-Convex Optimization with SARAH
Figure 4 for Optimal Finite-Sum Smooth Non-Convex Optimization with SARAH

  Access Paper or Ask Questions

PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach


Jan 07, 2019
Tsui-Wei Weng, Pin-Yu Chen, Lam M. Nguyen, Mark S. Squillante, Ivan Oseledets, Luca Daniel

Figure 1 for PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach
Figure 2 for PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach
Figure 3 for PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach
* updated ref [25] 
  Access Paper or Ask Questions

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks


Nov 29, 2018
Akhilan Boopathy, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel

Figure 1 for CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Figure 2 for CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Figure 3 for CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Figure 4 for CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
* Accepted by AAAI 2019 
  Access Paper or Ask Questions

Efficient Neural Network Robustness Certification with General Activation Functions


Nov 02, 2018
Huan Zhang, Tsui-Wei Weng, Pin-Yu Chen, Cho-Jui Hsieh, Luca Daniel

Figure 1 for Efficient Neural Network Robustness Certification with General Activation Functions
Figure 2 for Efficient Neural Network Robustness Certification with General Activation Functions
Figure 3 for Efficient Neural Network Robustness Certification with General Activation Functions
Figure 4 for Efficient Neural Network Robustness Certification with General Activation Functions
* Accepted by NIPS 2018. Huan Zhang and Tsui-Wei Weng contributed equally 
  Access Paper or Ask Questions

On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm


Oct 19, 2018
Tsui-Wei Weng, Huan Zhang, Pin-Yu Chen, Aurelie Lozano, Cho-Jui Hsieh, Luca Daniel

Figure 1 for On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm
Figure 2 for On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm
Figure 3 for On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm
Figure 4 for On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm
* Accepted by GlobalSIP 2018. Tsui-Wei Weng and Huan Zhang contributed equally 
  Access Paper or Ask Questions

Towards Fast Computation of Certified Robustness for ReLU Networks


Oct 02, 2018
Tsui-Wei Weng, Huan Zhang, Hongge Chen, Zhao Song, Cho-Jui Hsieh, Duane Boning, Inderjit S. Dhillon, Luca Daniel

Figure 1 for Towards Fast Computation of Certified Robustness for ReLU Networks
Figure 2 for Towards Fast Computation of Certified Robustness for ReLU Networks
Figure 3 for Towards Fast Computation of Certified Robustness for ReLU Networks
* Tsui-Wei Weng and Huan Zhang contributed equally 
  Access Paper or Ask Questions

Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach


Jan 31, 2018
Tsui-Wei Weng, Huan Zhang, Pin-Yu Chen, Jinfeng Yi, Dong Su, Yupeng Gao, Cho-Jui Hsieh, Luca Daniel

Figure 1 for Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
Figure 2 for Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
Figure 3 for Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
Figure 4 for Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
* Accepted by Sixth International Conference on Learning Representations (ICLR 2018). Tsui-Wei Weng and Huan Zhang contributed equally 
  Access Paper or Ask Questions