Skip to content

Our research areas

Secure and Robust Federated Learning thumbnail

Secure and Robust Federated Learning

Machine learning algorithms continue to achieve remarkable success in a wide range of applications. These advancements are possible, in part, due to the availability of large domain-specific datasets, for training machine learning models. Hence, there are expanding efforts to collect more representative data to train models for new applications. This raises serious concerns regarding the privacy and security of the collected data. The privacy ramifications of massive data collection in the machine learning landscape have led both industry and academia to work on alternative privacy preserving technologies for machine learning. Federated Learning is one such promising machine learning technology that advocates for a new decentralized learning paradigm that decouples data from model training, thus allowing users to retain data sovereignty. However, the large-scale and decentralized... Continue reading

Privacy Preserving Stream Analytics at Scale thumbnail

Privacy Preserving Stream Analytics at Scale

Recent years have seen unprecedented growth in networked devices and services that continuously collect increasingly detailed information about individuals. The collection of this unbounded stream of data is increasingly prevalent across a wide range of systems in diverse domains such as health, agriculture, transportation, operational insight, and smart cities. The growth of streaming data is largely attributed to the rising demand for instrumentation. Individuals and organizations are continuously logging various metrics that report systems’ state for better diagnoses, forecasting, decision making, and resource allocation. However, with this trend comes the problem of ensuring the privacy of user data. Users today typically entrust their data to a thirdparty storage or application provider. However, there is growing concern that this model leaves users vulnerable to privacy... Continue reading

End-to-End Designs for Data Privacy thumbnail

End-to-End Designs for Data Privacy

As we increasingly expose sensitive data to gain valuable insights and as regulatory privacy provisions are on the rise, the need to natively integrate privacy controls in data analytics frameworks is growing in importance. Today, privacy solutions are mostly ad hoc efforts that are implemented and enforced by data curators who have full access to data in the clear. Additionally, as these systems cannot provide proof of privacy compliance to end-users, there is no assurance that data processing complies with the stated privacy policy. In this project, we investigate a new cohesive end-to-end solutions to data privacy that follows the data from the source to downstream. Such solutions should be designed such that they can be easily integrated with existing data processing and analytics frameworks, coexist with data protection mechanisms in place and align with the strong notion of... Continue reading

Accessible Privacy Preserving Computation thumbnail

Accessible Privacy Preserving Computation

Secure computation enables us to ensure privacy while maintaining utility by using advanced cryptography, i.e., techniques beyond conventional symmetric- and public-key encryption, and authentication systems. Secure Multi-Party Computation (MPC), Zero-knowledge Proofs (ZP), and Fully Homomorphic Encryption (FHE) are becoming increasingly computationally feasible thanks to advances in the underlying theory, general hardware improvements, and more efficient implementations. While there is a growing number of research systems demonstrating practical solutions for a broader range of applications, real-world deployments of secure computation remain rare. Deploying such solutions currently requires extensive expert knowledge, including an in-depth understanding of the underlying cryptographic schemes. There is an increasing consensus among the community that accessibility is now a... Continue reading