I am an assistant professor at the College of Computing and Data Science at the Nanyang Technological University (NTU). I am broadly interested in Formal Methods and Programming Languages as well as Trustworthy AI and Safe Autonomy. Before joining NTU, I was an assistant professor at Singapore Management University (SMU). I obtained my PhD in 2023 at the Institute of Science and Technology Austria (ISTA), where I was fortunate to be advised 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 dorde.zikelic@ntu.edu.sg.

I have openings for motivated PhD students to work with me on topics listed below, or more broadly on topics related to formal methods, trustworthy AI or program verification. See this page for more details. Openings for other types of positions (postdocs, interns, visiting students) will be advertised later.

Research Interests

My research is concerned with designing theories and automated methods for ensuring that software and AI systems are correct, safe, and trustworthy. My research is both foundational and application driven. On the foundational side, the long-term goal of my work is to contribute to laying theoretical and algorithmic foundations of automated formal verification for probabilistic models and programs. Probabilistic models and programs provide a canonical framework for modelling and implementing computing systems that exhibit uncertain behaviour, with a broad range of applications such as randomised algorithms, communication protocols and networks, security and privacy protocols, control and autonomous systems, and AI. The central application domains that I focus on are trustworthy AI and safe autonomy. My goal is to develop certified learning and formal verification methods for designing trustworthy AI and safe autonomous systems, especially in the presence of uncertainty. My current research interests include:

1. Formal Methods for Probabilistic Models and Programs
   • Theory of verification of probabilistic systems
   • Probabilistic program verification
   • Verification and planning in Markov models
   • (non-probabilistic) Program verification
2. Trustworthy AI and Safe Autonomy
   • Formal verification and correct-by-construction design of AI-enabled control systems
   • Runtime monitoring and safeguarding of AI-enabled control systems
   • Safe and logic-guided reinforcement learning
   • Certified learning and formal verification of machine learning models
3. Broader perspective and other applications of probabilistic system verification:
   • Bidding games for auctions
   • Blockchain protocol analysis
   • Differential privacy

News

• July 2026. Several exciting activities coming up during FLOC 2026:
  • We will present our paper “Parallel Abstract Interpretation for Polynomial Programs with Range Bound Assertions” at CAV.
  • I will give an invited talk on “Neural Stochastic Control and Verification for Safe Autonomy” at SAIV.
  • I will give a talk on “SuperDP: Differential Privacy Refutation via Supermartingales” at VeriProP.
  • Ehsan Goharshady will give a talk on “Refuting Equivalence in Probabilistic Programs” at PERR.

• June 2026. We will organise a NII Shonan meeting on the Frontiers of Formal Methods for Probabilistic Models and Programs from June 22 - 26. Jointly organised with S. Akshay and Amir Goharshady.

• April-July 2026. I will attend ICLR 2026 in Rio de Janeiro, Brazil, PLDI 2026 in Denver, US, and FLOC 2026 in Lisbon, Portugal. If you will be around and would like to catch up or connect, please reach out.

• May 2026. Automated Approach for Solving Infinite-state Polynomial Reachability Games accepted at IJCAI 2026.

• April 2026. Parallel Abstract Interpretation for Polynomial Programs with Range Bound Assertions accepted at CAV 2026.

• April 2026. SuperDP: Differential Privacy Refutation via Supermartingales accepted at PLDI 2026.

• February 2026. Automating the Refinement of Reinforcement Learning Specifications accepted at ICLR 2026.

• December 2025. I gave an invited talk on “Neural Stochastic Control and Verification with Supermartingale Certificates” at the QuantFormal workshop at FSTTCS 2025 in Goa, India. Thank you for the invitation, I very much enjoyed the conference and many insightful discussions.

• October 2025. We will organise the second Singapore Programming Languages Summit on November 24, to be held at SMU. If you are a PL researcher based in Singapore (or will be visiting Singapore at the time), please consider participating and also presenting your work at the summit! More details here.