Deep Learning in Textual Low-Data Regimes for Cybersecurity

Dr. rer. nat. Markus Bayer is a research associate and post-doctoral researcher at the Chair of Science and Technology for Peace and Security (PEASEC) in the Department of Computer Science at the Technical University of Darmstadt.

• Introduction.- Research Design.- Findings.- Discussion.- Conclusion.- Information Overload in Crisis Management: Bilingual Evaluation of Embedding Models for Clustering Social Media Posts in Emergencies.- ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios.- A Survey on Data Augmentation for Text Classification.- Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers.- Design and Evaluation of Deep Learning Models for Real-Time Credibility Assessment in Twitter.- CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain.- Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence.- XAI-Attack: Utilizing Explainable AI to Find Incorrectly Learned Patterns for Black-Box Adversarial Example Creation.