Simin Chen

Simin Chen

Ph.D. Candidate of Computer Science

The University of Texas at Dallas

Biography

I am a fourth-year Ph.D. candidate at the University of Texas at Dallas (UTD). I am fortunate to be advised by Prof.Wei Yang and Prof.Cong Liu. Before joining UTD, I received my master degree from Tongji University in May 2018. My research interest lies in machine learning, computer security, and program analysis.

I am actively looking for cooperation in the following topics: (1) deploying ML models safely and efficiently on edge/server platforms, (2) developing automatic tools to find the bugs in existing ML infrastructures, and (3) understanding the decision making of ML models and improving them.

Feel free to drop me an email if we share common research interests.

Download my resumé.

Interests
  • Machine Learning
  • Computer Security
  • Software Engineering
Education
  • Ph.D. Candidate, 2019 - Now

    The University of Texas at Dallas

  • Master, 2015 - 2018

    Tongji University

  • Bachelor, 2011 - 2015

    Tongji University

Publications

(2024). PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models. In ESEC/FSE 2024.

PDF Code

(2023). Dynamic Transformer Provide a False Sense of Efficiency. In ACL 2023.

(2023). The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection. In CVPR 2023.

(2023). Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition. In CVPR 2023.

(2023). DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization. In ISSTA 2023.

(2022). NMTSloth: Understanding and Testing Efficiency Degradation of Neural Machine Translation Systems. In ESEC/FSE 2022.

PDF Code

(2022). Learning to Reverse DNNs from AI Programs Automatically. In IJCAI 2022.

PDF

(2022). NICGSlowDown: Evaluating the Efficiency Robustness of Neural Caption Generation Models. In CVPR 2022.

PDF Code Project

(2020). DENAS: automated rule generation by knowledge extraction from neural networks. In ESEC/FSE 2020.

PDF Code Project DOI

Experience

 
 
 
 
 
Research Assistant
NEC Laboratories America
Jan 2020 – May 2020 New Jersey
Apply ML techniques for program analysis.
 
 
 
 
 
Research Assistant
Microsoft Research
May 2021 – Jul 2020 Seattle
Evaluate the model leakage risk of on-device DNNs.

Contact