Education#

Northeastern University - Boston, MA#

PhD in Computer Science (Expected Jul. 2026)

• Research Areas: Trustworthy Machine Learning, Adversarial Machine Learning
• Advisors: Jonathan Ullman and Alina Oprea

Florida State University - Tallahassee, FL#

B.S. in Pure Mathematics (2017 - 2021)

• Honors Thesis: A Standardized Approach to Studying the Double Descent Phenomenon
• Advisors: Alec Kercheval and Nathan Crock

Work Experience#

Google Oct. 2024 - Aug. 2025#

Student Researcher | Cambridge, MA

• Topic: Machine Unlearning

LinkedIn Jun. 2024 - Aug. 2024#

Applied Research Intern | New York, NY

• Topic: Training Data Extraction from LLMs

LinkedIn Jun. 2023 - Aug. 2023#

Applied Research Intern | Mountain View, CA

• Topic: Differential Privacy for Analytics

Intuit May 2021 - Aug. 2021#

Software Engineering Intern | Mountain View, CA

Intuit May 2020 - Aug. 2020#

Software Engineering Intern | Mountain View, CA

NewSci Labs Aug. 2019 - May 2021#

Machine Learning Intern | Tallahassee, FL

Papers#

2025#

• Should We Forget About Certified Unlearning? Evaluating the Pitfalls of Noisy Methods John Abascal, Eleni Triantafillou, Matthew Jagielski, Nicole Mitchell, Peter Kairouz

• Black-Box Privacy Attacks on Shared Representations in Multitask Learning
  John Abascal, Nicolás Berrios, Alina Oprea, Jonathan Ullman, Adam Smith, Matthew Jagielski
  arXiv preprint

2024#

• Phantom: General Trigger Attacks on Retrieval Augmented Language Generation
  Harsh Chaudhari, Giorgio Severi, John Abascal, Matthew Jagielski, Christopher A. Choquette-Choo, Milad Nasr, Cristina Nita-Rotaru, Alina Oprea
  arXiv preprint

• TMI! Finetuned Models Leak Private Information from their Pretraining Data
  John Abascal, Stanley Wu, Alina Oprea, Jonathan Ullman
  Proceedings on Privacy Enhancing Technologies (PETS) 2024

2023#

• SNAP: Efficient Extraction of Private Properties with Poisoning
  Harsh Chaudhari, John Abascal, Alina Oprea, Matthew Jagielski, Florian Tramèr, Jonathan Ullman
  IEEE Symposium on Security and Privacy (S&P) 2023

Skills#

Programming Languages: Python, C++, C, Swift, SQL, JavaScript
Tools and Technologies: PyTorch, TensorFlow, scikit-learn, Hugging Face, NumPy, Pandas, GCP, Linux, UIKit Lanugages: English, Spanish

Contact#

Email: [email protected]
Office: 177 Huntington, Boston, MA 02115