Liang Tong

Email: ltong [at] nec-labs [dot] com

I am a research staff member in the Data Science & System Security Department at NEC Labs America, where I work on machine learning, data mining, and security.

I received my Ph.D. in CS from WashU (under supervision of Yevgeniy Vorobeychik), my M.S. in CS from Vanderbilt, and my M.Eng. & B.S. in communication engineering from UESTC.

Our department is actively hiring research interns (summer 2022) and full-time researchers. Please feel free to check here for details and email me if you are interested in working with us at NECLA.

CV  /  Google Scholar  /  Github

profile photo

Much of my work lies at the intersection of machine learning, artificial intelligence, and security, with the goal of building trustworthy machine learning systems that can directly benefit various domains such as computer vision, time series, and malware. More specifically, I am interested in using machine learning to improve system robustness and responsiveness, and improving reliability of the machine learning models themselves in dynamic environments. I have also worked on mobile cloud computing, in which I designed architectures and transmission schemes for offloading mobile AI applications to edge cloud.

FACESEC: A Fine-grained Robustness Evaluation Framework for Face Recognition Systems
Liang Tong, Zhengzhang Chen, Jingchao Ni, Dongjin Song, Wei Cheng, Haifeng Chen, Yevgeniy Vorobeychik
CVPR, 2021
supplement / arXiv / code / video / bibtex

A framework for systematizing adversarial evaluation of face recognition systems.

Defending Against Physically Realizable Attacks on Image Classification
Tong Wu, Liang Tong, Yevgeniy Vorobeychik
ICLR, 2020   (Spotlight Presentation)
arXiv / code / video / bibtex

Adversarial training with PGD attacks is not effective in defending against physically realizable attacks. Our design of a new threat model addresses this issue.

Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning
Liang Tong, Aron Laszka, Ning Zhang, Yevgeniy Vorobeychik
AAAI, 2020
arXiv (long version) / code / bibtex

We introduce a novel approach for computing a policy for prioritizing alerts in detection systems using adversarial reinforcement learning.

Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features
Liang Tong, Bo Li, Chen Hajaj, Chaowei Xiao, Ning Zhang, Yevgeniy Vorobeychik
USENIX Security, 2019
arXiv / code / video / bibtex

Conserved feature is the key for adversarial training to defend against real-world attacks.

Adversarial Regression with Multiple Learners
Liang Tong*, Sixie Yu*, Scott Alfeld, Yevgeniy Vorobeychik
ICML, 2018
supplement / arXiv / code / video / bibtex

We study the problem of adversarial linear regression with multiple learners and propose a game-theoretic approach for defense by modeling the interactions between the learners and the adversary.

Application-Aware Traffic Scheduling for Workload Offloading in Mobile Clouds
Liang Tong*, Wei Gao
INFOCOM, 2016   (Best Presentation in Session)
slides / bibtex

We adaptively balance the tradeoff between energy efficiency and responsiveness of mobile applications by developing application-aware wireless transmission schemes.

A Hierarchical Edge Cloud Architecture for Mobile Computing
Liang Tong*, Yong Li, Wei Gao
slides / bibtex

We propose to deploy cloud servers at the network edge and design the edge cloud as a tree hierarchy of geo-distributed servers, so as to efficiently utilize the cloud resources.

My Interns
  • Nauman Ahad (Georgia Tech): summer 2021
  • CSE 411A AI and Society (Fall 2019), Washington University in St. Louis
  • CSE 544T Special Topics in Computer Science Theory - Adversarial AI (Spring 2019), Washington University in St. Louis
  • CS 102 Introduction to Computer Science (Spring 2015), University of Tennessee
  • CS 160 Computer Organization (Fall 2014), University of Tennessee
  • Access Network Technology (Spring 2011), University of Electronic Science and Technology of China

Website credit: Jon Barron