About me
I am an Assistant Professor of Computer Science at the School of Computing and Information Systems at Singapore Management University. Previously, I obtained my PhD in 2023 at the Institute of Science and Technology Austria (ISTA), where I was fortunate to be supervised by Krishnendu Chatterjee and Petr Novotný. For my PhD work, I received the Outstanding PhD Thesis and the Outstanding Scientific Achievement awards at ISTA. Before that, I obtained bachelor’s and master’s degrees in mathematics at the University of Cambridge.
You can reach me at dzikelic@smu.edu.sg.
Openings
I have multiple openings for motivated PhD students, interns, and visiting PhD/master/undergrad students, to work with me on topics related to formal methods, trustworthy AI or program analysis. Please see this page if interested.
Research Interests
My research is concerned with helping programmers ensure that software and intelligent systems are correct, safe, robust and trustworthy. It lies at the intersection of Formal Methods, Artificial Intelligence and Programming Languages research. The long term goal of my research is to advance the theory and automation of formal reasoning about software and intelligent systems in the presence of uncertainty. Uncertainty may arise due to a plethora of reasons, including interaction with unknown environments, inference from data, randomization, interleaving of processes or multi-agent systems. My work is concerned with both theoretical aspects of formal reasoning under uncertainty, as well as the development of automated methods to help programmers build correct software and intelligent systems in practice. My current research interests (with references to some recent work) include:
- Program analysis of probabilistic programs (PLDI24, OOPSLA24, CAV22) and numerical programs (FM24, PLDI22, PLDI21)
- Safe learning for (stochastic) control and reinforcement learning (NeurIPS23, TACAS23, AAAI23, AAAI22)
- Formal methods for finite-state Markov models (IJCAI24a, IJCAI24b, CAV23)
- Formal methods for safe AI (AAAI23, NeurIPS21, AAAI21)
- Broader perspective and applications of probabilistic verification: Bidding games on graphs (ECAI23, AAAI23, SODA21); Blockchain protocols (PODC24)
See also my research statement for a more detailed overview of my work (last updated in December 2023).
News
July 2024. Visited Amir Goharshady at HKUST and gave a talk about Neural Controller Synthesis and Verification with Guarantees.
July 2024. Had a wonderful time attending and meeting students at the 20th International Summer School on Trustworthy Software, at ECNU in Shanghai, China. At the summer school, together with Tom Henzinger, we gave a lecture on Trustworthy AI through Neural Certificates, Runtime Monitoring, and Multi-Agent Reasoning.
June 2024. Sound and Complete Witnesses for Template-based Verification of LTL Properties on Polynomial Programs accepted at FM 2024.
May 2024. Visited Umang Mathur at National University of Singapore and gave a talk about A Learner-verifier Framework for Certifying Neural Controllers in Stochastic Systems.
May 2024. Visited S. Akshay at IIT Bombay and gave a talk about A Learner-verifier Framework for Certifying Neural Controllers in Stochastic Systems.
April 2024. Fully Automated Selfish Mining Analysis in Efficient Proof Systems Blockchains accepted at PODC 2024. Result of an exciting collaboration with cryptography researchers, in which we used probabilistic model checking to analyze and develop novel selfish mining attacks on efficient proof system blockchains.
- April 2024. Two papers accepted at IJCAI 2024:
- March 2024. Equivalence and Similarity Refutation for Probabilistic Programs accepted at PLDI 2024.