Sotabase

Career

· Assistant Professor, University of Illinois Urbana-Champaign2023–
· Postdoctoral Researcher, Microsoft2022–2023
· Modeling Intern, Lacework2021–2021
· Research Intern, Telefonica2021–2021
· Research Intern, Microsoft Research Cambridge2020–2021
· Research Assistant, University of Wisconsin-Madison2016–2022
· Visiting Researcher, University of Toronto

Publications (45)

Sparks of Artificial General Intelligence: Early experiments with GPT-4
arXiv.org · 2023
3,907
cited
Machine Unlearning
IEEE Symposium on Security and Privacy · 2019
1,237
cited
Unrolling SGD: Understanding Factors Influencing Machine Unlearning
European Symposium on Security and Privacy · 2021
279
cited
Exploring Connections Between Active Learning and Model Extraction
USENIX Security Symposium · 2018
181
cited
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
arXiv.org · 2020
151
cited
Proof-of-Learning: Definitions and Practice
IEEE Symposium on Security and Privacy · 2021
125
cited
Face-Off: Adversarial Face Obfuscation
Proceedings on Privacy Enhancing Technologies · 2020
50
cited
Verifiable and Provably Secure Machine Unlearning
2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · 2022
40
cited
A General Framework For Detecting Anomalous Inputs to DNN Classifiers
International Conference on Machine Learning · 2020
38
cited
Traversing the Quagmire that is Privacy in your Smart Home
IoT S&P@SIGCOMM · 2018
25
cited
Model Extraction and Active Learning
arXiv.org · 2018
24
cited
Proof-of-Learning is Currently More Broken Than You Think
European Symposium on Security and Privacy · 2022
24
cited
SoK: Machine Learning Governance
arXiv.org · 2021
20
cited
PowerCut and Obfuscator: An Exploration of the Design Space for Privacy-Preserving Interventions for Smart Speakers
SOUPS @ USENIX Security Symposium · 2018
19
cited
A Framework for Analyzing Spectrum Characteristics in Large Spatio-temporal Scales
ACM/IEEE International Conference on Mobile Computing and Networking · 2019
18
cited
Confidant: A Privacy Controller for Social Robots
IEEE/ACM International Conference on Human-Robot Interaction · 2022
18
cited
Hierarchical Federated Learning with Privacy
BigData Congress [Services Society] · 2022
15
cited
Characterizing Privacy Perceptions of Voice Assistants: A Technology Probe Study
arXiv.org · 2018
12
cited
Generating Semantic Adversarial Examples with Differentiable Rendering
arXiv.org · 2019
11
cited
Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers
arXiv.org · 2020
8
cited
Sotabase
Varun Chandrasekaran | Researcher Profile | Sotabase | Sotabase