Our research revolves around different aspects of technology to enable the development of socially responsible systems. Particular topics of interest are (more in our publications page)
Impact of Machine learning
The unstoppable explosion of machine learning algorithms in the recent years also has great impact in our daily activities. As much improvement as they bring, they also have negative effects and bring new challenges for research.
At the SPRING Lab we try to understand how machine learning has an on society, how it changes security and privacy problems, how we can use machine learning to help designers evaluate their systems design, as well as find principled ways to design defenses against machine learning-based attacks on privacy.
Related publications:
- Evading classifiers in discrete domains with provable optimality guarantees. Bogdan Kulynych, Jamie Hayes, Nikita Samarin, Carmela Troncoso. NeurIPS 2018 SecML Workshop.
- Questioning the assumptions behind fairness solutions. Critiquing and Correcting Trends in Machine Learning. Rebekah Overdorf, Bogdan Kulynych, Ero Balsa, Carmela Troncoso, Seda Gürses. CRACT NeurIPS 2018 Workshop.
Privacy evaluation
As systems become increasingly complex, they gather, and expose, increasing amounts of data . This information can be extracted from content, but also meta-data (timing patterns, locations, etc).
At the SPRING Lab we work on building tools to enable users to better understand how much information they reveal, and to enable app developers to achieve their goals without endangering the privacy of users that altruistically contribute to the projects.
Related publications:
- Encrypted DNS –> Privacy? A Traffic Analysis Perspective. Sandra Siby, Marc Juarez, Claudia Diaz, Narseo Vallina-Rodriguez, Carmela Troncoso. Pre-print. 2019.
- Rethinking Location Privacy for Unknown Mobility Behaviors. Simon Oya, Carmela Troncoso, Fernando Pérez-González. EuroS&P 2019.
- On the (lack of) location privacy in crowdsourcing applications. Spyros Boukoros, Mathias Humbert, Stefan Katzenbeisser, Carmela Troncoso. Usenix Security 2019.
- Knock Knock, Who’s There? Membership Inference on Aggregate Location Data. Apostolos Pyrgelis, Carmela Troncoso, and Emiliano De Cristofaro. NDSS 2018.
Engineering privacy-preserving systems
The privacy concerns stemming from the pervasiveness of on-line services and mobile devices in our daily lives has put Privacy Technologies in the spotlight. Yet, despite the many years of research on these technologies it is still not well understood how to design them, evaluate them, and incorporate them into ICT systems in a systematic manner. This lack of understanding hinders the development of solutions that enable citizens, governments, and corporations to enjoy technological progress without damaging our societal values.
At the SPRING Lab we work on developing building blocks that engineers can use to build privacy-preserving systems, and methodologies that allow them to reason in a systematic manner both about the design and the evaluation of privacy-preserving technologies.
Related publications:
- ClaimChain: Improving the Security and Privacy of In-band Key Distribution for Messaging. Bogdan Kulynych, Wouter Lueks, Marios Isaakidis, George Danezis, and Carmela Troncoso. WPES 2018.
- Lightnion: seamless anonymous communication from any web browser. Wouter Lueks, Matthieu Daumas, Carmela Troncoso. Workshop on Measurements, Attacks and Defenses for the Web (MADWeb) 2019.
- Systematizing Decentralization and Privacy: Lessons from 15 years of research and deployments. Carmela Troncoso, Marios Isaakidis, George Danezis, and Harry Halpin. PoPETS 2017.
- Engineering Privacy by Design Reloaded. Seda Gurses, Carmela Troncoso, and Claudia Diaz. Amsterdam Privacy Conference 2015.