Systems security and data privacy

Stefan Dziembowski


Polish computer scientist, professor of exact and natural sciences. He specializes in cryptography. Professor of the Institute of Computer Science at the Faculty of Mathematics, Computer Science and Mechanics at the University of Warsaw


Several machine learning applications involve issues where privacy plays a special role. This includes cases in which secrecy applies to the training data (e.g., when it contains medical information) and those in which the algorithm itself is subject to protection because, for example, it reveals specific information about the training data. Our group is engaged in developing methods to protect such privacy. In particular, we are investigating solutions based on multiparty computation protocols technology. This technology allows calculations to be performed on distributed data so that the data is not revealed to outsiders. A related method we are also investigating in this context is the so-called homomorphic encryption, which further minimizes the need for interaction between the parties executing the algorithm. In addition, our research looks at possible applications of the so-called trusted execution environments to increase the privacy of the computations performed. A separate direction, which we are also investigating, is to ensure that the result of the computation does not reveal private information about the input data, using a technology called differential privacy. The method is based on appropriately adding random noise to the result, so that information about individual elements of the input data cannot be deduced from it.

The above-mentioned technologies have been developed in theoretical computer science for many years. The added value of our research comes from direct contact with IDEAS in machine learning researchers. These interactions allow us to tailor solutions to specific problems occurring in this field of research.


One of the main problems with multi-agent cryptographic protocols is that decentralized solutions tend to be more complex and error-prone than centralized solutions, and errors in such protocols lead to significant financial losses. At IDEAS, we address these problems with tools derived from formal methods. In particular, we are working on using methods from machine learning to prove the correctness of cryptographic protocols. This is a promising approach, as in many cases, the analysis has repeatable elements that can potentially be automated. The challenge, however, is finding the right training data.


Blockchain technology was introduced in 2008. The name is usually understood as cryptographic protocols for large-scale consensus in distributed networks. These protocols can operate in the so-called permissionless variant, in which the set of participants is not defined a priori, or in the permissioned variant, in which consensus is maintained by predefined groups of servers. Initial applications of this technology were in the financial sector, mainly for creating new virtual cryptocurrencies (such as bitcoin). However, the technology is now considered to have many more applications, particularly in digital identity management systems, mortgage management, land registration systems, supply chain monitoring, insurance, clinical trials, copyright management, running decentralized organizations, energy trading management, or the Internet of Things (loT). At IDEAS, we study practical aspects of this technology, such as the security of so-called cryptocurrency wallets, consensus protocols, or smart contracts.

Publications of team members as part of research work at IDEAS NCBR


Conference name Data Links Document title Author(s)
27 November - 4 December 2022
The Surprising Effectiveness of Latent World Models for Continual Reinforcement Learning
Piotr Miłoś, Gracjan Góral, Mateusz Olko
Subquadratic Dynamic Path Reporting in Directed Graphs Against an Adaptive Adversary
Stefan Dziembowski, Tomasz Lizurej
04.11.2022 - 06.11.2022
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
Piotr Miłoś

Stefan Dziembowski


Professional experience

Stefan Dziembowski is a professor at the University of Warsaw. He is interested in theoretical and applied cryptography. His research interests relate to theoretical and applied cryptography, in particular issues related to physical attacks on cryptographic devices, and blockchain technology. Dziembowski received an MSc degree in computer science in 1996 from the University of Warsaw, and a PhD degree in computer science in 2001 from the University of Aarhus, Denmark. He was a post-doc at the ETH Zurich, CNR Pisa and the University of Rome “La Sapienza”, where he joined the faculty in 2008. In 2010 he moved to the University of Warsaw where he leads the Cryptography and Blockchain Lab.

Awards and achievements

His papers appeared at leading computer science conferences (FOCS, STOC, CRYPTO, EUROCRYPT, ASIACRYPT, IEEE S&P, ACM CCS, TCC, CT-RSA, and LICS), and journals (Journal of Cryptology and IEEE Transactions on Information Theory, Journal of the ACM, Communications of the ACM). He also served as a PC member of several international conferences, including CRYPTO, EUROCRYPT, ASIACRYPT, Theory of Cryptography Conference (TCC), and the International Colloquium on Automata, Languages and Programming (ICALP). He served as the general chair of the Twelfth Theory of Cryptography Conference (TCC’15), and as a PC co-chair of TCC’18. He will serve as a PC co-hair of Eurocrypt 2022. He was also a keynote speaker at the Conference on Cryptographic Hardware and Embedded Systems (CHES) 2020. He is a co-author of two papers that won the Best Paper Awards (at Eurocrypt 2014 and at IEEE S&P 2014).


He is a recipient of an ERC Advanced Grant, ERC Starting Independent Researcher Grant, an FNP Welcome grant, an FNP Team grant, two NCN “Opus” grants, and a Marie-Curie Intra-European Fellowship (2006-2007).   He is also a winner of the Polish-German “Copernicus” Award (in 2020, together with prof. Sebastian Faust) and the Kazimierz Bartel award (in 2016). He will serve as a member of the Council of the Polish National Science Centre in the 2021-24 term.


Algorithms, especially the ones used in machine learning, promise to aid people in making decisions.

Blockchain technology was introduced in 2008. Several machine learning applications involve issues where privacy plays a special role.

Today, both science and industry rely heavily on machine learning models, predominantly artificial neural networks.

Skip to content