Hi! I am Anna, a second-year PhD student at
Cornell University, advised by
Sainyam Galhotra.
My research spans a wide range of interests,
currently focusing on testing knowledge removal in AI systems and
evaluating their reliability, with an emphasis on understanding
their limits and ensuring trustworthy deployment.
Before starting at Cornell, I completed my MS in Computer Science at UIUC,
advised by Tianyin Xu.
There, my research centered around cloud systems reliability.
Work Experience
Research Assistant - Cornell Bowers CIS
Aug. 2025 – Present | USA
- Causality-based Fuzzing for Machine Unlearning Verification
- Tooling to Detect Residual Influence at Data-point and Feature Levels
- Evaluating both Direct and Indirect Causal Effects in Black-box Models
- Benchmarks Across Multiple Datasets and Model Architectures
Research Assistant - xlab, UIUC
Sep. 2022 – May 2024 | USA
- Local Developer Testing and Cloud Emulation
- REST API Analysis of Azure Storage, AWS S3, and DynamoDB
- Breaking down Emulator's Fidelity using Differential Fuzzing
- Tooling for Testing Cloud-based Software in CI/CD Environments
Research Assistant - Networks and Systems Group, LUMS
Jun. 2020 – May 2022 | Pakistan
- Webpage Load Performance Testing on Low-end Devices
- Tooling for Reducing Webpage Complexity
- Lighthouse, Puppeteer, and WebPageTest
Research Intern - dlab, EPFL
Jun. 2021 – Dec. 2021 | Switzerland
- Natural Language Processing (NLP)
- React Web Development
Education
- Cornell University(2024 – Present)Ph.D. in Computer Science
- UIUC(2022 – 2024)MS in Computer Science
- LUMS(2018 – 2022)BS in Computer Science
Publications
Causal Fuzzing for Verifying Machine Unlearning
[pdf] |
[bib]
Anna Mazhar, and Sainyam Galhotra
In submission (Preprint arXiv:2509.16525)
Fidelity of Cloud Emulators: The Imitation Game of Testing Cloud-based Software
[pdf] |
[bib] |
[slides] |
[talk]
Anna Mazhar, Saad Sher Alam, William Zheng, Yinfang Chen, Suman Nath, and Tianyin Xu
International Conference on Software Engineering (ICSE'25)
Selected Projects
- Evaluating Multi-Agent Reasoning Frameworks | Python, LangGraph, AutoGen (Sep. 2025 - Present)
Evaluating multiple multi-agent reasoning frameworks on diverse mathematical reasoning benchmarks to study their coordination dynamics and reliability.Investigating how different agent coordination schemes and feedback loops influence collective reasoning quality and problem-solving performance. - Verifying AVL in Coq | Coq (Oct. 2024 - Dec. 2024)
Implementing and formally verifying the operations of AVL tree data structure using Coq proof assistant. - Multi-Writer Multi-Reader Shared Registers | Go, gRPC, Protobuf (Apr. 2023 - May 2023)
Implemented a MWMR Shared Register protocol with fault tolerance and data consistency through quorum-based operations. - Raft | Go (Oct. 2021 – Nov. 2021)
Built a fault-tolerant key-value storage service using the Raft consensus algorithm for log replication and leader election. - QuestSpace | ReactJS, MongoDB, ExpressJS, Node.js, AWS (Feb. 2021 – Apr. 2021)
Developed a MERN-stack web app for hosting competitions with quizzes, rapid-fire, and submission rounds.
Selected Awards
- SIGSOFT Travel Grant - Travel support for attending conferences
- Erasmus Mundus Scholarship (€49000) - Awarded to 26 applicants out of 735.
- Summer@EPFL Fellowship - Selected from ~4500 applicants with 1-2% acceptance rate.
- LUMS Merit Scholarship Award (5000 USD) - For academic excellence.
- Dean’s Honor List (LUMS) - Recognized three consecutive times for academic performance.
