Van Hentenryck’s research on privacy focuses on applied differential privacy for complex applications in mobility, energy, census data, and other areas, as well as privacy-preserving federated data sharing. The primary focus is on isolating differential privacy techniques that are accurate enough for sophisticated analytic tasks, including optimization and machine learning. Another focus is to understand the bias introduced by privacy mechanisms and their impact on decision making. In addition, there are some truly intriguing issues to investigate at the intersection of fairness and privacy.
2022
- Post-processing of Differentially Private Data: A Fairness Perspective, Keyu Zhu, Ferdinando Fioretto, and Pascal Van Hentenryck. In the Proceedings of the Joint International Conference on Artificial Intelligence (IJCAI-ECAI2022), Vienna, Austria.
- Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey. Ferdinando Fioretto, Cuong Tran, Pascal Van Hentenryck, and Keyu Zhu. In the Proceedings of the Joint International Conference on Artifcial Intelligence (IJCAI-ECAI2022), Vienna, Austria.
2021
- Differentially Private Optimal Power Flow for Distribution Grids. Vladimir Dvorkin, Ferdinando Fioretto Pascal Van Hentenryck, Pierre Pinson, and Jalal Kazempour. IEEE Transactions on Power Systems. 36(3), 2186–2196, 2021.
- Differential Privacy of Hierarchical Census Data: An Optimization Approach, Ferdinando Fioretto, Pascal Van Hentenryck, and Keyu Zhu, Artificial Intelligence, 296, July 2021.
- Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach. Cuong Tran, Ferdinando Fioretto, and Pascal Van Hentenryck. Proceeding of The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), February, 2021.
- Bias and Variance of Post-processing in Differential Privacy. Keyu Zhu, Pascal Van Hentenryck, and Ferdinando Fioretto. Proceeding of The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), February, 2021.
2020
- Privacy-Preserving Obfuscation for Distributed Power Systems. Fernandino Fioretto, Terrence Mak, and Pascal Van Hentenryck. Electric Power Systems Research.
- Differentially Private Distributed Optimal Power Flow. Vladimir Dvorkin, P. Van Hentenryck, Jalal Kazempour, Pierre Pinson. Proceedings of the 2020 59th IEEE Conference on Decision and Control (CDC-2020), December 2020.
- Differential Privacy for Stackelberg Games. Ferdinando Fioretto, Lesia Mitridati, and Pascal Van Hentenryck. In the Proceedings of 29th International Joint Conference on Artificial Intelligence (IJCAI-20), Tokyo, Japan 2020.
- Privacy-Preserving Power System Obfuscation: A Bilevel Optimization Approach. Terrence Mak, Fernandino Fioretto, Lyndon Shi, and Pascal Van Hentenryck. IEEE Transactions on Power Systems, 35(2), 1627–1637, March 2020.
- Differential Privacy for Power Grid Obfuscation. Fernandino Fioretto, Terrence Mak, and Pascal Van Hentenryck. IEEE Transactions on Smart Grids. 11(2), 1356– 1366, March 2020.
2019
- Differential Privacy of Hierarchical Census Data: An Optimization Approach, Fernandino Fioretto and Pascal Van Hentenryck. n Proceedings of the International Conference on Principles and Practice of Constraint Programming (CP), 2019.
- OptStream: Releasing Time Series Privately. Ferdinando Fioretto, Terrence W.K. Mak, and Pascal Van Hentenryck, Journal of Artificial Intelligence Research (JAIR), 65, 423–456, 2019.
- Privacy-Preserving Obfuscation of Critical Infrastructure Networks. Fernandino Fioretto, Terrence Mak, and Pascal Van Hentenryck. In the Proceedings of 28th International Joint Conference on Artificial Intelligence (IJCAI-19), Macao, China, 2019.
- Privacy-Preserving Federated Data Sharing. Fernandino Fioretto and Pascal Van Hentenryck. In the Proceedings of 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019), Montreal, Canada, 2019.
- Differential Privacy for Power Grid Obfuscation, Ferdinando Fioretto, Terrence W.K. Mak, Pascal Van Hentenryck, arXiv:1901.06949 [cs.AI].
2018
- Constrained-Based Differential Privacy for Mobility Services. Fernandino Fioretto, Chansoo Lee, and Pascal Van Hentenryck. In the Proceedings of 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2018), Stock- holm, Sweden. 2–7, July 11–13, 2018.
- Constrained-based Differential Privacy: Releasing Optimal Power Flow Benchmarks Privately, Ferdinando Fioretto and Pascal Van Hentenryck. 15th International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, Delft, The Netherlands, June 26-29, 2018.