Erik Derner

Associate Scientist

erikderner.en.md photo

Erik Derner is a researcher at the Czech Technical University (CTU) in Prague, Czech Republic. He currently co-leads the task on security and safety of multimodal generalist foundation models (MGFMs) in the ELLIOT project. Previously, he worked as ELLIS Postdoctoral Researcher at ELLIS Alicante, focusing on the societal and ethical implications of generative AI, including safety, security, psychological aspects, and biases in low-resource languages. He received his Ph.D. in Robotics and Artificial Intelligence from CTU in Prague in 2022. His Ph.D. thesis was honored with the Werner von Siemens Award in the Industry 4.0 category and with the CTU FEE Dean’s Award for a Prestigious Dissertation.

Website: https://erik-derner.github.io/research/
Link to ORCID profile: ORCID iD icon https://orcid.org/0000-0002-7588-7668

Publications in association with ELLIS Alicante

2025

09/29
Arnaiz-Rodríguez, A., Baidal, M., Derner, E., Layton Annable, J., Ball, M., Ince, M., Perez Vallejos, E., & Oliver, N. (2025). Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs. Under review.
08/04
Hagendorff, T., Derner, E., & Oliver, N. (2025). Large Reasoning Models Are Autonomous Jailbreak Agents. arXiv:2508.04039.
08/01
Vienna, AT
Derner, E., Sansalvador de la Fuente, S., Gutiérrez, Y., Moreda, P., & Oliver, N. (2025). Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora. 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP), ACL 2025.
08/01
Vienna, AT
Derner, E., & Batistič, K. (2025). Beyond Words: Multilingual and Multimodal Red Teaming of MLLMs. First Workshop on LLM Security (LLMSEC), ACL 2025.
07/31
Vienna, AT
Derner, E., & Batistič, K. (2025). Gender Representation Bias Analysis in LLM-Generated Czech and Slovenian Texts. 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025), ACL 2025.
07/31
Vienna, AT
Baidal, M., Derner, E., & Oliver, N. (2025). Guardians of Trust: Risks and Opportunities for LLMs in Mental Health. Fourth Workshop on NLP for Positive Impact (NLP4PI), ACL 2025.
02/25
Philadelphia, US
Derner, E., Sansalvador de la Fuente, S., Gutiérrez, Y., Moreda, P., & Oliver, N. (2025). Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora. Collaborative AI and modeling of Humans (CAIHu) - Bridge program at AAAI 2025.

2024

08/26
Derner, E., Batistič, K., Zahálka, J., & Babuška, R. (2024). A Security Risk Taxonomy for Prompt-Based Interaction with Large Language Models. IEEE Access, 12, 126176-126187.
07/23
Derner, E., Kučera, D., Oliver, N., & Zahálka, J. (2024). Can ChatGPT Read Who You Are?. Computers in Human Behavior: Artificial Humans, 2(2), 100088.
06/19
Derner, E., Sansalvador de la Fuente, S., Gutiérrez, Y., Moreda, P., & Oliver, N. (2024). Leveraging Large Language Models to Measure Gender Bias in Gendered Languages. arXiv:2406.13677.
02/21
Vancouver, CA
Derner, E., Kučera, D., Oliver, N., & Zahálka, J. (2024). Can ChatGPT Read Who You Are?. Collaborative AI and Modeling of Humans, AAAI Bridge Program.

2023

12/26
Derner, E., Kučera, D., Oliver, N., & Zahálka, J. (2023). Can ChatGPT Read Who You Are?. arXiv:2312.16070.
11/19
Derner, E., Batistič, K., Zahálka, J., & Babuška, R. (2023). A Security Risk Taxonomy for Large Language Models. arXiv preprint arXiv:2311.11415.