Area of research
Artificial Intelligence · Computational Theory and Mathematics
Research interest
Research interests include Computer science, Artificial intelligence, Mathematics, Combinatorics, Backdoor, and Computer security.
User Strategization and Trustworthy Algorithms
Model metamers reveal divergent invariances between biological and artificial neural networks
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Faster Sparse Minimum Cost Flow by Electrical Flow Localization
Implementation Matters in Deep RL: A Case Study on PPO and TRPO
International Conference on Learning Representations 2020cited by 119position: last
Circulation Control for Faster Minimum Cost Flow in Unit-Capacity Graphs
Image Synthesis with a Single (Robust) Classifier
DSpace@MIT (Massachusetts Institute of Technology) 2019cited by 62position: last
Adversarially Robust Generalization Requires More Data
DSpace@MIT (Massachusetts Institute of Technology) 2018cited by 282position: last
Spectral Signatures in Backdoor Attacks
DSpace@MIT (Massachusetts Institute of Technology) 2018cited by 169position: last
Round compression for parallel matching algorithms
Prior convictions: Black-box adversarial attacks with bandits and priors
DSpace@MIT (Massachusetts Institute of Technology) 2018cited by 68position: last
Training for faster adversarial robustness verification via inducing Relu stability
DSpace@MIT (Massachusetts Institute of Technology) 2018cited by 62position: last
An <i>O</i>(log <i>n</i>/log log <i>n</i>)-Approximation Algorithm for the Asymmetric Traveling Salesman Problem
Matrix Scaling and Balancing via Box Constrained Newton's Method and Interior Point Methods
On the Resiliency of Static Forwarding Tables
Computing Maximum Flow with Augmenting Electrical Flows