Publications

Ondřej Lukáš, Jihoon Shin, Emilia Rivas, Diego Forni, Maria Rigaki, Carlos Catania, Aritran Piplai, Christopher Kiekintveld, Sebastian Garcia (2026). Evaluating Generalization Mechanisms in Autonomous Cyber Attack Agents. arXiv preprint.

Maria Rigaki, Carlos A. Catania, Sebastian Garcia (2026). Building Adaptative and Transparent Cyber Agents with Local Language Models. Expert Systems with Applications, 299.

Ondřej Kobza, Adam Černý, Ivan Dostál, Jan Šedivý, Maria Rigaki, Muris Sladić, Sebastian Garcia (2026). AlquistCoder: A Synthetic Data Approach to Training Compact Secure Coding Assistants and Building Security Benchmarks. Computational Intelligence, 42(4).

Maria Rigaki (2025). Offensive Applications of Machine Learning in Cybersecurity. PhD Dissertation, Czech Technical University in Prague.

Maria Rigaki, Carlos Catania, Sebastian Garcia (2024). Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments. arXiv preprint.

Maria Rigaki, Ondřej Lukáš, Carlos Catania, Sebastian Garcia (2024). Prompt. Exploit. Repeat: Automating Network Security Testing with LLMs. International Conference on Agents and Artificial Intelligence (ICAART), 15–36.

Maria Rigaki, Sebastian Garcia (2023). Stealing and evading malware classifiers and antivirus at low false positive conditions. Computers & Security, 129.

Maria Rigaki, Sebastian Garcia (2023). A Survey of Privacy Attacks in Machine Learning. ACM Computing Surveys, 56(4).

Maria Rigaki, Sebastian Garcia (2023). The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning. ESORICS 2023.

Maria Rigaki, Ondrej Lukas, Carlos Catania, Sebastian Garcia (2023). Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments. International Conference on Agents and Artificial Intelligence (ICAART), 3, 774–781.