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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Higher-Order Certification for Randomized Smoothing

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

* Accepted to NeurIPS2020(spotlight) 

  Access Paper or Ask Questions

Optimizing Mode Connectivity via Neuron Alignment

Sep 05, 2020
N. Joseph Tatro, Pin-Yu Chen, Payel Das, Igor Melnyk, Prasanna Sattigeri, Rongjie Lai

* 24 pages, 9 figures, code available at https://github.com/IBM/NeuronAlignment 

  Access Paper or Ask Questions

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases

Jul 31, 2020
Ren Wang, Gaoyuan Zhang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong, Meng Wang


  Access Paper or Ask Questions

Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources

Jul 29, 2020
Yun-Yun Tsai, Pin-Yu Chen, Tsung-Yi Ho


  Access Paper or Ask Questions

Proper Network Interpretability Helps Adversarial Robustness in Classification

Jun 26, 2020
Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Cynthia Liu, Pin-Yu Chen, Shiyu Chang, Luca Daniel

* 22 pages, 9 figures, Published at ICML 2020 

  Access Paper or Ask Questions

Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case

Jun 25, 2020
Shuai Zhang, Meng Wang, Sijia Liu, Pin-Yu Chen, Jinjun Xiong

* International Conference on Machine Learning (ICML 2020) 

  Access Paper or Ask Questions

A Dynamical Systems Approach for Convergence of the Bayesian EM Algorithm

Jun 23, 2020
Orlando Romero, Subhro Das, Pin-Yu Chen, Sérgio Pequito


  Access Paper or Ask Questions

A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning

Jun 21, 2020
Sijia Liu, Pin-Yu Chen, Bhavya Kailkhura, Gaoyuan Zhang, Alfred Hero, Pramod K. Varshney

* IEEE Signal Processing Magazine 

  Access Paper or Ask Questions

Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics

May 22, 2020
Payel Das, Tom Sercu, Kahini Wadhawan, Inkit Padhi, Sebastian Gehrmann, Flaviu Cipcigan, Vijil Chenthamarakshan, Hendrik Strobelt, Cicero dos Santos, Pin-Yu Chen, Yi Yan Yang, Jeremy Tan, James Hedrick, Jason Crain, Aleksandra Mojsilovic


  Access Paper or Ask Questions

Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness

Apr 30, 2020
Pu Zhao, Pin-Yu Chen, Payel Das, Karthikeyan Natesan Ramamurthy, Xue Lin

* accepted by ICLR 2020 

  Access Paper or Ask Questions

Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement

Mar 31, 2020
Chao-Han Huck Yang, Jun Qi, Pin-Yu Chen, Xiaoli Ma, Chin-Hui Lee

* The first draft was finished in August 2019. Accepted to IEEE ICASSP 2020 

  Access Paper or Ask Questions

Rethinking Randomized Smoothing for Adversarial Robustness

Mar 02, 2020
Jeet Mohapatra, Ching-Yun Ko, Tsui-Wei, Weng, Sijia Liu, Pin-Yu Chen, Luca Daniel

* Jeet Mohapatra and Ching-Yun Ko contributed equally 

  Access Paper or Ask Questions

Defending against Backdoor Attack on Deep Neural Networks

Feb 26, 2020
Hao Cheng, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Pu Zhao, Xue Lin

* Accepted by KDD 2019 AdvML workshop 

  Access Paper or Ask Questions

Towards an Efficient and General Framework of Robust Training for Graph Neural Networks

Feb 25, 2020
Kaidi Xu, Sijia Liu, Pin-Yu Chen, Mengshu Sun, Caiwen Ding, Bhavya Kailkhura, Xue Lin

* Accepted by ICASSP 2020 

  Access Paper or Ask Questions

Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning

Feb 20, 2020
Chao-Han Huck Yang, Jun Qi, Pin-Yu Chen, Yi Ouyang, I-Te Danny Hung, Chin-Hui Lee, Xiaoli Ma

* Accepted to IEEE ICASSP 2020 

  Access Paper or Ask Questions

AdvMS: A Multi-source Multi-cost Defense Against Adversarial Attacks

Feb 19, 2020
Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin

* Accepted by 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020) 

  Access Paper or Ask Questions

Block Switching: A Stochastic Approach for Deep Learning Security

Feb 18, 2020
Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin

* Accepted by AdvML19: Workshop on Adversarial Learning Methods for Machine Learning and Data Mining at KDD, Anchorage, Alaska, USA, August 5th, 2019, 5 pages 

  Access Paper or Ask Questions

Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent

Feb 18, 2020
Pu Zhao, Pin-Yu Chen, Siyue Wang, Xue Lin

* accepted by AAAI 2020 

  Access Paper or Ask Questions

CAT: Customized Adversarial Training for Improved Robustness

Feb 17, 2020
Minhao Cheng, Qi Lei, Pin-Yu Chen, Inderjit Dhillon, Cho-Jui Hsieh


  Access Paper or Ask Questions

Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States

Feb 09, 2020
Yunan Ye, Hengzhi Pei, Boxin Wang, Pin-Yu Chen, Yada Zhu, Jun Xiao, Bo Li

* AAAI 2020 

  Access Paper or Ask Questions

Towards Verifying Robustness of Neural Networks Against Semantic Perturbations

Dec 19, 2019
Jeet Mohapatra, Tsui-Wei, Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel


  Access Paper or Ask Questions

Adversarial T-shirt! Evading Person Detectors in A Physical World

Nov 27, 2019
Kaidi Xu, Gaoyuan Zhang, Sijia Liu, Quanfu Fan, Mengshu Sun, Hongge Chen, Pin-Yu Chen, Yanzhi Wang, Xue Lin


  Access Paper or Ask Questions

Evading Real-Time Person Detectors by Adversarial T-shirt

Oct 18, 2019
Kaidi Xu, Gaoyuan Zhang, Sijia Liu, Quanfu Fan, Mengshu Sun, Hongge Chen, Pin-Yu Chen, Yanzhi Wang, Xue Lin


  Access Paper or Ask Questions

An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy

Oct 17, 2019
Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, Kush R. Varshney


  Access Paper or Ask Questions

Sign-OPT: A Query-Efficient Hard-label Adversarial Attack

Sep 28, 2019
Minhao Cheng, Simranjit Singh, Patrick Chen, Pin-Yu Chen, Sijia Liu, Cho-Jui Hsieh


  Access Paper or Ask Questions

One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques

Sep 14, 2019
Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovińá, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang


  Access Paper or Ask Questions