Sai Yerramreddy

Hi, I'm Sai Yerramreddy

Software Testing, Artificial Intelligence, AI Robustness, AI Interpretability


About Me

I am a second-year Ph.D. student in the Department of Computer Science at the University of Maryland (UMD), College Park, where I am advised by Prof. Adam Porter. My research primarily focuses on developing testing and interpretability pipelines for software and AI algorithms.

I previously also earned my Masters in Computer Science from University of Maryland. Currently I work with Dr. Justyna Zwolak on analyzing feature engineering and interpretability techniques for detecting dark solitons in Bose-Einstein condensates as a part of the NIST Professional Research Experience Program (PREP). Additionally, I also collaborate with Fraunhofer CMA on studying boundaries and improving the robustness of bioinformatics classifiers. In the past, I have also worked with Prof. Leilani Battle and Prof. Dominik Moritz on modeling user behavior and optimizing visualization tools.

When I'm not working, you can find me on the football field (or soccer field, as some might say), hiking, playing video games, or whipping up some delicious meals in the kitchen. And if all else fails, I'll probably just be napping. After all, being a PhD student is exhausting!

Skills

ML Libraries: Tensorflow, PyTorch, Keras, OpenCV, scikit-learn
Programming Languages: Python, Kotlin, JavaScript, TypeScript, C, Java
Backend: Flask, NodeJs, Django, Firebase
Frontend: Web (Angular, React), Android
DataBases: MySQL, DuckDB, DB2, SQLite
CI/CD: Git, Github Actions, Docker, Latex
Visualization Tools: Tableau, Power BI, D3.js, Matplotlib

Recent News

April 2023: Website is live!
Jan 2023: Started working with NIST as a part of PREP
Jan 2023: Paper got accepted to EMSE Journal
March 2022: SIGMOD demo paper got accepted
Jan 2022: Paper got accepted to AAAI Workshop

  Publications

When I get involved in a project, I don't just complete it. I walk an extra mile ahead to make it better than requested. Below are some of my projects. Check out my Github for more open sources.


An empirical assessment of machine learning approaches for triaging reports of static analysis tools

Sai Yerramreddy, Austin Mordahl, Ugur Koc, Shiyi Wei, Jeffrey Foster, Marine Carpuat, Adam Porter

Empirical Software Engineering Journal


Demonstration of VegaPlus (Scalable Vega): Optimizing Declarative Visualization Languages

Junran Yang, Hyekang Kevin Joo, Sai S Yerramreddy, Siyao Li, Dominik Moritz, Leilani Battle

SIGMOD '22: Demo Paper


FLORIDA: Metamorphic Adversarial Input Detection Pipeline for Face Recognition Systems

Rohan Reddy Mekala, Sai S Yerramreddy, Adam A Porter

The AAAI-22 Workshop on Adversarial Machine Learning and Beyond (AAAI-22 AdvML Workshop)


Genetic Algorithm for Optimal Feature Vector Selection in Facial Recognition

Sai Yerremreddy, KTV Talele, Yash Kokate

2019 IEEE 5th International Conference for Convergence in Technology (I2CT)


An automated facial recognition attendance system leveraging custom iot cameras

Royston Dmello, Sai Yerremreddy, Samriddha Basu, Tejas Bhitle, Yash Kokate, Prachi Gharpure

2019 9th IEEE Confluence


Machine Learning Approach for Diagnosis of Autism Spectrum Disorders

Sai Yerramreddy, Samriddha Basu, Ananya D Ojha, Dhananjay Kalbande

Proceedings of ICICC 2019, Springer Singapore


  Professional & Teaching Experience


09-Jan-2023 to Present

National Institute of Standards & Technology, Gaithersburg, MD

Graduate PREP Researcher

Conducting an empirical evaluation of feature engineering and neural network approaches for classifying dark solitons in Bose-Einstein condensates. Furthermore, we also aim to assess and enhance interpretability techniques related to the evaluated classification methods, in order to highlight the areas of interest for human evaluation.


01-Feb-2020 to Present

University of Maryland (Fraunhofer USA CMA), College Park, MD

Graduate Research Assistant

Developed a metamorphic adversarial detection pipeline for face recognition systems. Conducted an empirical study of machine learning algorithms (Bag of Words, LSTM, and GNN) to detect false positive reports being generated by static analysis tools. Working on a testing suite and data generation framework for AI based metagenomics software.


21-May-2018 to 20-Jul-2018

Ugam Solutions Pvt. Ltd, Bangalore, India

Consultant Intern

Built a smart retail algorithm to detect SKUs on grocery aisles. Also developed an automated annotation tool using Flask and Angular.js for generating brief analytical reports based on the detection.


Fall 19, Spring 22, Fall 22

University of Maryland, College Park, MD

Graduate Teaching Assistant

TA for CMSC436: Programming Handheld Systems. Developed labs and testing suites. Helped students with their academic projects and assignments. Organized schedule for other TAs. Proctored and graded midterms and finals.


  Education

  • 2015 - 2019
    Sardar Patel Institute of Technology, Mumbai

    Bachelors of Engineering in Computer Science

  • 2019 - 2021
    University of Maryland, College Park

    Master of Science in Computer Science

  • 2022 - Present
    University of Maryland, College Park

    PhD in Computer Science