Johannes Bjerring Bjerva

Johannes Bjerring Bjerva is a Professor at Aalborg University specializing in Language Technology. He leads the Sapere Aude-funded project Building TRUST in Text, which focuses on detecting adversarial manipulation of large language models (LLMs) to ensure their reliability and trustworthiness across languages.

• Educated at Stockholm University (PhD in NLP) and Hamar Cathedral School
• Research interests: Computational Linguistics, AI Security, Multilingual NLP, Linguistic Signal Analysis
• Recipient of Sapere Aude: DFF-Research Leaders 2025 grant and DFF-Forskningsleder-bevillingen

His project addresses critical challenges in identifying poisoned LLM outputs through subtle linguistic fingerprints, with societal implications for healthcare, education, and finance. He collaborates with Stockholm University and NVIDIA to develop scalable detection methods.

Scientific Awards:

• Sapere Aude: DFF-Research Leaders 2025 grant
• DFF-Forskningsleder-bevillingen

Johannes advises two PhD students and a postdoc within his research group, emphasizing interdisciplinary approaches to secure AI systems. His work balances foundational research with practical applications to make LLMs safer for global use.