Dr. Arvind Narayanan
Professor of Computer Science
Sources checkedProfessor of Computer Science at Princeton University and Director of the Center for Information Technology Policy (CITP). Co-author of 'AI Snake Oil'. Leading international researcher in data privacy, algorithmic accountability, and the socio-technical impacts of artificial intelligence. Named to TIME100 in AI.
Areas of focus
Professional niches
Proof of Work
Evaluating the Fairness and Accuracy of Algorithmic Risk Assessment Instruments
Authored the classic tutorial and survey demonstrating the mathematical impossibility of satisfying three common notions of algorithmic fairness simultaneously, proving the need for explicit ethical trade-offs in automated scoring.
Mathematical trade-off proofs assume stationary data distributions and cannot resolve normative political disagreements regarding priority.
Context: COMPAS recidivism scores, credit risk models, calibration vs error-rate parity statistical constraints.
View missionDe-anonymization and Privacy Risks in Large-Scale Data Platforms
Proved that high-dimensional datasets (Netflix Prize, social graphs) can be re-identified with high probability using sparse auxiliary information, refuting the concept of 'anonymized' behavioral data in machine learning training sets.
Modern differential privacy mechanisms mitigate some vulnerability but introduce bounded utility trade-offs in downstream model training.
Context: High-dimensional matrix factorizations, graph matching algorithms, differential privacy formulations.
View mission