His main research concerns Robustness, Artificial neural network, MNIST database, Artificial intelligence and Theoretical computer science. His study in Robustness is interdisciplinary in nature, drawing from both Contextual image classification, Algorithm, Enhanced Data Rates for GSM Evolution and Computer security. He combines subjects such as Function, Rate of convergence, Estimator and Stochastic optimization with his study of Artificial neural network.
He has included themes like Importance sampling, Natural language processing, Classifier, Coordinate descent and Optimization problem in his MNIST database study. His research investigates the link between Artificial intelligence and topics such as Machine learning that cross with problems in Bilinear interpolation. His studies in Theoretical computer science integrate themes in fields like Adversarial system, Graph neural networks, Topology, Task and Perspective.
Pin-Yu Chen mainly focuses on Artificial intelligence, Robustness, Artificial neural network, Machine learning and Adversarial system. His Artificial intelligence study combines topics in areas such as Metric and Natural language processing. The study incorporates disciplines such as Adversary, Contextual image classification, MNIST database, Convolutional neural network and Algorithm in addition to Robustness.
His Artificial neural network research includes elements of Embedding and Bounded function. Pin-Yu Chen performs multidisciplinary study in the fields of Machine learning and Zeroth order via his papers. His Adversarial system research is multidisciplinary, incorporating elements of Computer security, Interpretability, Theoretical computer science and Deep neural networks.
His primary areas of investigation include Artificial intelligence, Robustness, Machine learning, Artificial neural network and Adversarial system. All of his Artificial intelligence and Deep learning, Contextual image classification, MNIST database, Image and Gradient descent investigations are sub-components of the entire Artificial intelligence study. His work carried out in the field of Robustness brings together such families of science as Smoothing, Adversary, Regularization, Sensitivity and Optimization problem.
His Interpretability and Transfer of learning study in the realm of Machine learning interacts with subjects such as Scalability and Zeroth order. His Artificial neural network research is multidisciplinary, incorporating perspectives in Network architecture, Backdoor, Bounded function, Range and Algorithm. His Adversarial system research includes themes of Computer security, Robotic arm and Navigation system.
Pin-Yu Chen spends much of his time researching Artificial intelligence, Robustness, Artificial neural network, Machine learning and Adversarial system. Many of his research projects under Artificial intelligence are closely connected to Detector with Detector, tying the diverse disciplines of science together. His research integrates issues of Contextual image classification and Algorithm, Optimization problem in his study of Robustness.
His Artificial neural network research incorporates themes from Network architecture, Backdoor and Rational design. His studies examine the connections between Machine learning and genetics, as well as such issues in Adversary, with regards to Natural gradient. His Adversarial system study which covers MNIST database that intersects with Interpretability, Directional derivative and Oracle.
This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.
ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models
Pin-Yu Chen;Huan Zhang;Yash Sharma;Jinfeng Yi.
Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security (2017)
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples.
Pin-Yu Chen;Yash Sharma;Huan Zhang;Jinfeng Yi.
national conference on artificial intelligence (2017)
Is Robustness the Cost of Accuracy? – A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
Dong Su;Huan Zhang;Hongge Chen;Jinfeng Yi.
european conference on computer vision (2018)
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
Amit Dhurandhar;Pin-Yu Chen;Ronny Luss;Chun-Chen Tu.
neural information processing systems (2018)
Efficient Neural Network Robustness Certification with General Activation Functions
Huan Zhang;Tsui-Wei Weng;Pin-Yu Chen;Cho-Jui Hsieh.
neural information processing systems (2018)
Smart attacks in smart grid communication networks
Pin-Yu Chen;Shin-Ming Cheng;Kwang-Cheng Chen.
IEEE Communications Magazine (2012)
AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks
Chun-Chen Tu;Paishun Ting;Pin-Yu Chen;Sijia Liu.
national conference on artificial intelligence (2019)
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Vijay Arya;Rachel K. E. Bellamy;Pin-Yu Chen;Amit Dhurandhar.
arXiv: Artificial Intelligence (2019)
On Modeling Malware Propagation in Generalized Social Networks
Shin-Ming Cheng;Weng Chon Ao;Pin-Yu Chen;Kwang-Cheng Chen.
IEEE Communications Letters (2011)
Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach
Minhao Cheng;Thong Le;Pin-Yu Chen;Jinfeng Yi.
arXiv: Learning (2018)
Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking d-index is inferred from publications deemed to belong to the considered discipline.
If you think any of the details on this page are incorrect, let us know.
We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below: