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 with the Turner Dissertatin Award (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 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
Research

I have a strong passion in understanding when and why machine learning fails, and how to prevent the failures.

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.

Towards Deploying Robust Machine Learning Systems
Liang Tong
Doctoral dissertation, Washington University in St. Louis, 2021   (Turner Dissertation Award, the best Ph.D. thesis of WashU CS)
bibtex

A systematic study on adversarial evaluation, defense, and deployment of ML systems.

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

Is robust ML really robust in the face of physically realizable attacks on image classifications? This paper provides a rethinking of adversarial robustness.

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

A robust ML model is not the end of the story. We need to deal with the false-positive alerts raised by ML models.

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

Is robust ML really robust in the face of real attacks on malware classifiers? If no, how to bridge the gap?

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

What if there are multiple ML models and a single adversary? What should be their optimal strategies?

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

How to adaptively balance the tradeoff between energy efficiency and responsiveness of mobile applications if they are offloaded to edge cloud?

A Hierarchical Edge Cloud Architecture for Mobile Computing
Liang Tong, Yong Li, Wei Gao
INFOCOM, 2016   (The 2nd most cited paper at INFOCOM'16)
slides / bibtex

The first work on hierarchical edge cloud architecture for mobile applications.

Patents
My Interns
  • Nauman Ahad (Georgia Tech): summer 2021
Teaching
  • 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