TEAM

Our Team

Serify aims at making cutting-edge security intelligence accessible to security teams worldwide. Our team uniquely combines expertise in automated security information retrieval and adaptive deep learning in low-data regimes, proven through years of research and real-world prototypes.

Dr.-Ing. Philipp Kühn

Co-Founder & Product Owner

Philipp's research focuses on automated threat intelligence retrieval and processing, leveraging Natural Language Processing and Large Language Models to optimise the CTI cycle. Alongside his research, he has led teams of up to 56 people across 5 groups, bringing hands-on experience in personnel leadership and agile project management to building Serify.

Dr. rer. nat. Markus Bayer

Co-Founder & AI Research Lead

Markus specialises in developing cutting-edge techniques such as active learning, data augmentation, transfer learning, and adversarial training to enhance the robustness and precision of machine learning models in cybersecurity applications. His doctoral thesis focused on Deep Learning in Textual Low-Data Regimes for Cybersecurity.

Our research and contributions to the field

Ready to enhance your security operations?

Join security teams leveraging AI-powered intelligence to protect their organisations, from CSIRTs and SOCs to NIS2-regulated enterprises.

Get in Touch Learn More

Our Team

Dr.-Ing. Philipp Kühn

Dr. rer. nat. Markus Bayer

Publications (25)

Deep Learning in Textual Low-Data Regimes for Cybersecurity

Proactive Cyber Threat Intelligence: Automating the Intelligence Cycle based on Open Sources

Reducing Information Overload: Because Even Security Experts Need to Blink

Bandit on the Hunt: Dynamic Crawling for Cyber Threat Intelligence

A survey of machine learning models and datasets for the multi-label classification of textual hate speech in english

XAI-Attack: Utilizing Explainable AI to Find Incorrectly Learned Patterns for Black-Box Adversarial Example Creation

ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios

‘We Do Not Have the Capacity to Monitor All Media’: A Design Case Study on Cyber Situational Awareness in Computer Emergency Response Teams

CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain

Navigating the Shadows: Manual and Semi-Automated Evaluation of the Dark Web for Cyber Threat Intelligence

ThreatCrawl: A BERT-based Focused Crawler for the Cybersecurity Domain

Multi-level fine-tuning, data augmentation, and few-shot learning for specialized cyber threat intelligence

Common vulnerability scoring system prediction based on open source intelligence information sources

Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers

Survey on Data Augmentation for Text Classification

The Notion of Relevance in Cybersecurity: A Categorization of Security Tools and Deduction of Relevance Notions

Reducing Information Overload: Because Even Security Experts Need to Blink

Help Wanted - Challenges in Data Collection, Analysis and Communication of Cyber Threats in Security Operation Centers

Design and Evaluation of Deep Learning Models for Real-Time Credibility Assessment in Twitter

OVANA: An Approach to Analyze and Improve the Information Quality of Vulnerability Databases

CySecAlert: An Alert Generation System for Cyber Security Events Using Open Source Intelligence Data

CYWARN: Strategy and Technology Development for Cross-Platform Cyber Situational Awareness and Actor-Specific Cyber Threat Communication

Information Overload in Crisis Management: Bilingual Evaluation of Embedding Models for Clustering Social Media Posts in Emergencies

Rapid relevance classification of social media posts in disasters and emergencies: A system and evaluation featuring active, incremental and online learning

Sharing of Cyber Threat Intelligence between States

Ready to enhance your security operations?