activity
20182022
most citedDesign of intentional backdoors in sequential models

19 citations · 21 across the 4 of their papers we have counts for

collaborators

6 papers

cs.RO20222 cited

Uncertainty-aware Perception Models for Off-road Autonomous Unmanned Ground Vehicles

Zhaoyuan Yang, Yewteck Tan, Shiraj Sen +4

Off-road autonomous unmanned ground vehicles (UGVs) are being developed for military and commercial use to deliver crucial supplies in remote locations, help with mapping and surve…

cs.LG2022

Dropout Inference with Non-Uniform Weight Scaling

Zhaoyuan Yang, Arpit Jain

Dropout as regularization has been used extensively to prevent overfitting for training neural networks. During training, units and their connections are randomly dropped, which co…

cs.CR2021

On Adversarial Vulnerability of PHM algorithms: An Initial Study

Weizhong Yan, Zhaoyuan Yang, Jianwei Qiu

With proliferation of deep learning (DL) applications in diverse domains, vulnerability of DL models to adversarial attacks has become an increasingly interesting research topic in…

cs.LG2020

Variational Encoder-based Reliable Classification

Chitresh Bhushan, Zhaoyuan Yang, Nurali Virani +1

Machine learning models provide statistically impressive results which might be individually unreliable. To provide reliability, we propose an Epistemic Classifier (EC) that can pr…

cs.CR201919 cited

Design of intentional backdoors in sequential models

Zhaoyuan Yang, Naresh Iyer, Johan Reimann +1

Recent work has demonstrated robust mechanisms by which attacks can be orchestrated on machine learning models. In contrast to adversarial examples, backdoor or trojan attacks embe…

cs.LG2018

Adversarial Reinforcement Learning for Observer Design in Autonomous Systems under Cyber Attacks

Abhishek Gupta, Zhaoyuan Yang

Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. Th…