Dr S. Picek (Stjepan)

• Matteo Cardaioli, Stefano Cecconello, Mauro Conti, and Simone Milani, Stjepan Picek, Eugen Saraci: Hand Me Your PIN! Inferring ATM PINs of Users Typing with a Covered Hand. USENIX Security Symposium 2022 Full text
• Shivam Bhasin, Anupam Chattopadhyay, Annelie Heuser, Dirmanto Jap, Stjepan Picek, Ritu Ranjan Shrivastwa. Mind the Portability: A Warriors Guide through Realistic Profiled Side-channel Analysis. NDSS 2020. Full text
• Lejla Batina, Shivam Bhasin, Dirmanto Jap, Stjepan Picek. CSI NN: Reverse Engineering of Neural Network Architectures Through Electromagnetic Side Channel. USENIX Security Symposium 2019: 515-532. Full text
• Stjepan Picek, Annelie Heuser, Alan Jovic, Shivam Bhasin, Francesco Regazzoni: The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations. IACR Trans. Cryptogr. Hardw. Embed. Syst. 2019(1): 209-237 (2019) Full text
• Jaehun Kim, Stjepan Picek, Annelie Heuser, Shivam Bhasin, Alan Hanjalic: Make Some Noise. Unleashing the Power of Convolutional Neural Networks for Profiled Side-channel Analysis. IACR Trans. Cryptogr. Hardw. Embed. Syst. 2019(3): 148-179 (2019) Full text

• Radboud Repository
• Research Information Services (RIS)
• Google Scholar

H index: 28

• 2019 - Best paper award: Walter Krawec, Stjepan Picek, Domagoj Jakobovic: Evolutionary Algorithms for the Design of Quantum Protocols. International Conference on the Applications of Evolutionary Computation (Part of EvoStar) More information

• 2015 - 2018 Evolutionary computation algorithms represent a range of problem-solving techniques based on principles of biological evolution, like natural selection and genetic inheritance. Such algorithms can be used to solve a variety of difficult problems, among which are those from the area of cryptography. Examples of such an approach include the evolving hash functions or creation of a new block cipher. First results in this area have emerged over 30 years ago, and in recent years there has been an increased interest in this area. Still, some problems like problem formulation and representation remain open. This project deals with various applications of optimization and learning with evolutionary computation in cryptography. The project is fully funded by the Croatian science foundation under the contract IP-2014-09-4882. More information
• 2021 - 2024 Small devices like transportation and bank cards are typical targets for adversaries looking into creative ways to break them, often using various side channels. This proposal will consider machine learning algorithms in order to assess the strengths of such adversaries and to protect our devices and data. More information
• 2021 - 2025 Modern society is interconnected through electronic and mobile devices, which we call the Internet of Things (IoT). The lack of proper protection mechanisms can lead to privacy violations and financial loss. The goal of PROACT is to design novel algorithms and silicon chips with inherent protection against physical attacks, and to develop novel simulation and evaluation techniques for physical security. PROACT will therefore contribute to an increased protection of our personal and company-critical data.

• AI and Security - Seminar
• Bachelor Thesis
• Master Thesis Computing Science
• Master Thesis Information Sciences
• Research Internship
• Security and Privacy of Machine Learning

• Assistant professor, TU Delft (01 October 2021 - 30 September 2025)
  Faculty of Electrical Engineering, Mathematics & Computer Science