4 papers
Directional Influence Function: Estimating Training Data Influence in Constrained Learning
Xin Wang, R. Tyrrell Rockafellar, Xuegang +1
As constrained learning becomes increasingly common, models are trained under explicit feasibility requirements to enforce fairness, safety, robustness, regulariza- tion, and physi…
Machine Unlearning of Traffic State Estimation and Prediction
Xin Wang, R. Tyrrell Rockafellar, Xuegang +1
Data-driven traffic state estimation and prediction (TSEP) relies heavily on data sources that contain sensitive information. While the abundance of data has fueled significant bre…
Model-Targeted Data Poisoning Attacks against ITS Applications with Provable Convergence
Xin Wang, Feilong Wang, Yuan Hong +3
The growing reliance of intelligent systems on data makes the systems vulnerable to data poisoning attacks. Such attacks could compromise machine learning or deep learning models b…
Set-Valued Sensitivity Analysis of Deep Neural Networks
Xin Wang, Feilong Wang, Xuegang Ban
This paper proposes a sensitivity analysis framework based on set valued mapping for deep neural networks (DNN) to understand and compute how the solutions (model weights) of DNN r…