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
Towards Reliable Testing for Machine Unlearning
Anna Mazhar, and Sainyam Galhotra
Foundations of Software Engineering (FSE'26 -- Ideas, Visions and Reflections)
Causal Fuzzing for Verifying Machine Unlearning
[pdf] |
[arXiv]
Anna Mazhar, and Sainyam Galhotra
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, Xinze Zheng, Yinfang Chen, Suman Nath, and Tianyin Xu
International Conference on Software Engineering (ICSE'25)
Selected Projects
- Evidence Degradation in Multi-Agent Workflows
Analyzing evidence degradation in multi-agent workflows using perturbation-based evaluation. Demonstrated that minor corruptions in inputs (e.g., OCR errors, table misalignment) systematically alter workflow traces, with implications for reliability in retrieval-based AI systems. - Causal Verification Framework for Machine Unlearning
Designed a causal influence-based verification framework for Machine Unlearning that detects hidden data residuals missed by existing approaches, advancing the debuggability of ML systems. - Cloud Emulator Fidelity Testing
Led the first systematic study of behavioral fidelity in cloud emulators (Azurite, LocalStack), uncovering discrepancies in 94 of 255 APIs across AWS and Azure via a custom SDK fuzzer. Resulted in 12 confirmed bugs and 6 upstream fixes.
Selected Awards
- Erasmus Mundus Scholarship (€49000) - Awarded to 26 applicants out of 735
- Summer@EPFL Fellowship - Selected from ~4500 applicants with 1-2% acceptance rate
- SIGSOFT Travel Grant - Travel support for attending conferences
