About

I am currently a third year PhD student in the School of Informatics at the University of Edinburgh and a member of the Laboratory for Foundations of Computer Science (LFCS). My core area of study is private machine learning, particularly Differential Privacy.

I am interested in a range of theoretical and applied topics within machine learning, including submodular optimization, algorithmic stability, sequence-to-sequence prediction tasks and regularization.

My research goal is to contribute to the integrity of machine learning, both in terms of reliability and ethical considerations such as privacy and fairness.

Blog Posts

An Introduction to Differential Privacy

Your Database isn't Anonymous

Experience

June - October 2021

Research Intern: Facebook AI Applied Research.

Topic: High-precision membership inference attacks against machine learning models.

Education

2022 (Expected): PhD Computer Science: Laboratory for Foundations of Computer Science, School of Informatics, University of Edinburgh
2018: MSc Artificial Intelligence: University of Edinburgh (Awarded with Distinction)
Thesis Title: What is Multi-Task Learning actually learning? An investigation into the effects of Multi-Task Learning for Sequence-to-Sequence Neural Models of Morphology [PDF]

IBM Shortlist for best Machine Learning Practical project
Dissertation listed as one of the ‘Outstanding Project Submissions 2017-18’

2016: BA Mathematics: Trinity College Dublin (First Class Honours)
Thesis Title: Bayesian Inference for Stochastic Volatility Models

Publications

Papers

L. Watson, C. Guo, G. Cormode and A. Sablayrolles On the Importance of Difficulty Calibration in Membership Inference Attacks , ICLR 2022. [PDF][Video]

L. Watson, A. Mediratta, T. Elahi, and R. Sarkar Privacy Preserving Detection of Path Bias Attacks in Tor, Proceedings on Privacy Enhancing Technologies (PETs), 2020. [PDF] [Video]

B. Rozemberczki, L. Watson, P. Bayer, H.T. Yang, O. Kiss, S. Nilsson and R. Sarkar The Shapley Value in Machine Learning, IJCAI Survey Track 2022 [PDF][Video]

Preprints

L. Watson, R. Andreeva, H.T. Yang, and R. Sarkar Differentially Private Shapley Values for Data Evaluation, 2022. [PDF]

L. Watson, A. Ghosh, B. Rozemberczki and R. Sarkar Continual and Sliding Window Release for Private Empirical Risk Minimization, 2021. [PDF]

L. Watson, B. Rozemberczki and R. Sarkar Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent, 2020. [PDF]

Teaching Support

Accelerated Natural Language Processing, Autumn 2018, 2019 & 2020 (Tutor, Lab Demonstrator and/or Marker)

Natural Language Understanding, Generation and Machine Translation, Spring 2019 & 2020 (Lab Demonstrator, Marker)

Social and Technological Networks, Autumn 2019 (Teaching Assistant)

INF2 - Introduction to Algorithms and Data Structures, Spring 2020 (Marker)

Data-driven Business and Behaviour Analytics, Autumn 2020 (Teaching Assistant)

Machine Learning Theory, Spring 2022 (Teaching Assistant)

Contact

Email: lauren.watson [at] ed.ac.uk

Office: IF-5.19, Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB

Lauren Watson