I am a Postdoctoral Research Scientist in the Center for Cybersecurity at Columbia University's Data Science Institute, advised by Junfeng Yang and Jason Healey. I received my PhD in Computer Science from the University of Chicago, advised by Aloni Cohen. My research interests lie broadly in the field of trustworthy data science, and in particular, in the robustness, privacy, and statistical validity of machine learning systems. Some of my recent work has involved designing and analyzing adversarial training algorithms for machine learning models under strengthened adversarial assumptions and analyzing the utility of differentially private US Census data for downstream policy-relevant use cases like legislative redistricting.
Outside of academia, I've worked on private machine learning as a software engineering intern at Meta. I completed my undergraduate degree at Brown University in 2020, concentrating in computer science and urban studies.
Understanding and
Mitigating the Impacts of Differentially Private
Census Data on State Level Redistricting
C. Cianfarani, A. Cohen.
Election Law Journal, 2026.
Adapting to Evolving
Adversaries with Regularized Continual Robust
Training
S. Dai*, C. Cianfarani*, A. Bhagoji, V. Sehwag, P. Mittal.
ICML 2025.
Understanding Robust
Learning through the Lens of Representation
Similarities.
C. Cianfarani*, A. Bhagoji*, V. Sehwag*, B. Zhao, H. Zheng, and
P. Mittal.
NeurIPS 2022.
'Hello, It's Me':
Deep Learning-based Speech Synthesis Attacks in the Real
World.
E. Wenger, M. Bronckers, C.
Cianfarani, J. Cryan, A. Sha, H. Zheng, and B. Zhao.
CCS
2021.
Elasticity
of Workloads and Periods of Parallel Real-Time
Tasks.
J. Orr, C. Gill, K. Agrawal, S. Baruah, C. Cianfarani, P.
Ang, and C. Wong.
RTNS 2018.
Modeling Deletion Requests
in Machine Unlearning.
C. Cianfarani, A. Cohen.
cc5672 'at' columbia 'dot' edu