Our Journey

Development of research prototypes for automated security information detection and adaptive deep learning at PEASEC, TU Darmstadt.

Dr. Bayer's work centres on enhancing the performance of deep learning models in low-data cybersecurity environments through methods such as active learning, data augmentation, and adversarial training. His research integrates large language models like GPT-4 to improve model robustness and applicability, addressing real-world security challenges and bridging academic insights with industrial needs.

Complementing this, Dr. Kühn focuses on information retrieval from public data and the use of Natural Language Processing and Large Language Models to strengthen IT security. His research combines technical innovation with an understanding of intergovernmental cybersecurity collaboration, emphasising the balance between automation and human expertise.

Together, their research efforts contribute to key projects including CYLENCE, CYWARN, ATHENE, emergenCITY, and SecUrban, driving forward interdisciplinary solutions for digital security and societal resilience.

Pursuing pre-seed resources and external validation for the Serify platform: applying to the StartUpSecure programme for cybersecurity startup funding, building contacts with hessian.AI for compute resources and access to its startup network, and taking part in structured mentoring to sharpen the business model and go-to-market strategy.

Building a functional demonstrator of the integrated Serify platform, comprising four core components: a cybersecurity Knowledge Base aggregating threat intelligence from 500,000+ monitored sources; an eight-agent multi-agent pipeline for automated extraction of IOCs, TTPs, threat actors, CVEs, and campaign data; a web-based Chat Interface enabling natural-language interaction with security analysts; and a REST API for programmatic integration. The demonstrator is jointly evaluated with CSIRT and SOC personnel to validate real-world applicability.

Launch of a structured pilot programme with 2–4 selected CSIRT and SOC teams in the DACH region. Pilot partners validate the platform in their operational environments and provide direct feedback to shape further development, supported by strong regulatory tailwinds driving urgent demand for automated threat intelligence.

Formal founding of Serify as a university spinoff from TU Darmstadt, backed by public startup funding. With institutional support from PEASEC and compute resources from Hessian.AI, transitioning from a research demonstrator to a commercially deployed SaaS product for the European cybersecurity market.

Onboarding the first pilot users of the productised Serify platform. Early customers run Serify in day-to-day operations, and their feedback drives hardening, integrations, and workflow refinements ahead of general availability.

Public launch of the Serify SaaS platform for CSIRT teams, SOC analysts, and NIS2-affected organisations across Europe. Tiered subscription plans enable deployment from SMEs to large-scale security operations, with optional on-premise deployment for high-security environments.

Continuous capability expansion based on customer feedback, broadening from the DACH market to the wider European CTI landscape with growing teams across engineering, sales, and customer success.