Fnu Suya

Fnu Suya

Assistant Professor

EECS@University of Tennessee, Knoxville

suya[at]utk[dot]edu

Biography

I am a tenure-track Assistant Professor in the Min H. Kao Department of Electrical Engineering and Computer Science at the University of Tennessee, Knoxville. From Oct 2023 to July 2024, I was a MC2 Postdoctoral Fellow at the Maryland Cybersecurity Center (MC2) at the University of Maryland, College Park. I received my Ph.D. degree in Computer Science from the University of Virginia, advised by Prof. David Evans and Prof. Yuan Tian at UCLA. I am interested in machine learning for security and the trustworthy aspects of machine learning, especially in malicious training environments.

I am looking for self-motivated students to work on trustworthy machine learning and machine learning for security. If you are interested, please fill out the questionnaire and send me an email at suya[at]utk[dot]edu.

News:

  • Started my new role as an assistant professor. I will be teaching “Intro to Cybersecurity” this fall!

Materials:

Interests
  • Trustworhy Machine Learning
  • Machine Learning for Security
Education

  • Ph.D. in Computer Science

    University of Virginia

  • B.Eng. (Honors) in Electrical Engineering

    China Agricultural University

Selected Publications

Quickly discover relevant content by filtering publications.
Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans (2024). SoK: Pitfalls in Evaluating Black-Box Attacks. In IEEE SaTML 2024.

PDF Cite Code

Fnu Suya, Xiao Zhang, Yuan Tian, David Evans (2023). What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?. In NeurIPS 2023.

PDF Cite Poster

Yulong Tian, Fnu Suya, Anshuman Suri, Fengyuan Xu, David Evans (2023). Manipulating Transfer Learning for Property Inference. In CVPR 2023.

PDF Cite Code Video

Evan Rose, Fnu Suya, David Evans (2022). Poisoning Attacks and Subpopulation Susceptibility. In VISxAI 2022 (Best Paper Award).

PDF Cite Code

Yulong Tian, Fnu Suya, Fengyuan Xu, David Evans (2022). Stealthy Backdoors as Compression Artifacts. In TIFS 2022.

PDF Cite Code

Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans, Yuan Tian (2021). Model-Targeted Poisoning Attacks with Provable Convergence. In ICML, 2021.

PDF Cite Code Poster Slides

Fnu Suya, Jianfeng Chi, David Evans, Yuan Tian (2019). Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries. In Usenix Security 2020.

PDF Cite Code Slides Video

See all publications

Experience

 
 
 
 
 
University of Maryland, College Park
MC2 Postdoctoral Fellow
University of Maryland, College Park
Oct 2023 – Present Maryland, USA
Research on machine learning for security and poisoning for beneficial outcomes.
 
 
 
 
 
University of Virginia
Graduate Research Assistant
University of Virginia
Aug 2017 – Aug 2023 Virginia, USA
Research on trustworthy machine learning at SRG.
 
 
 
 
 
Qualcomm AI Research
Interim Engineering Intern
Qualcomm AI Research
May 2021 – Aug 2021 San Diego, USA (remote)
Robust federated learning against backdoor attacks.
 
 
 
 
 
Amazon Web Services
Applied Scientist Intern
Amazon Web Services
Jan 2021 – Apr 2021 New York City, USA (remote)
Worked on GNN based anomaly detection on extremely large graphs.
 
 
 
 
 
Bosch AI Center
Research Intern
Bosch AI Center
Jun 2020 – Aug 2020 Pittsburgh, USA (remote)
Worked on query efficient black-box attacks on vision classifiers.

Researched Topics

adversarial attacks adversarial examples attack taxonomy backdoor attacks batch attacks bayesian optimization black-box attacks cloud-RAN data poisoning attacks distribution inference indiscriminate poisoning attacks model compression pretrained model manipulation property inference provable convergence query based attacks subpopulation poisoning attacks transfer attacks transfer learning variation in susceptibility

Contact