Markus Bayer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Markus Bayer has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Christian Reuter
Wissenschaft und Technik für Frieden und Sicherheit (PEASEC), Technische Universität Darmstadt, Darmstadt, Deutschland
9 shared publications - Marc-André Kaufhold
Technical University of Darmstadt
4 shared publications - Philipp Kuehn
Technical University of Darmstadt
4 shared publications - Thea Riebe
Science and Technology for Peace and Security (PEASEC), Technical University of Darmstadt, Darmstadt, Germany
2 shared publications Tobias Frey
Technical University of Darmstadt
2 shared publicationsBjörn Buchhold
CID GmbH, Freigericht, Germany
1 shared publication
Latest Publications
- Open Access
- 7 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (6) , 1-39
A Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in English
The dissemination of online hate speech can have serious negative consequences for individuals, online communities, and entire societies. This and the large volume of hateful online content prompted both practitioners’, e.g., in content moderation or law enforcement and researchers’ interest in machine learning models to automatically classify instances of hate speech. Whereas most scientific works address hate speech classification as a binary task, practice often requires a differentiation into sub-types, e.g., according to target, severity, or legality, which may overlap for individual content. Hence, researchers created datasets and machine learning models that approach hate speech classification in textual data as a multi-label problem. This work presents the first systematic and comprehensive survey of scientific literature on this emerging research landscape in English (N = 46). We contribute with a concise overview of 28 datasets suited for training multi-label classification models, revealing significant heterogeneity regarding label-set, size, meta-concept, annotation process, and inter-annotator agreement. Our analysis of 24 publications proposing suitable classification models further establishes inconsistency in evaluation and a preference for architectures based on Bidirectional Encoder Representation from Transformers (BERT) and Recurrent Neural Networks (RNNs). We identify imbalanced training data, reliance on crowdsourcing platforms, small and sparse datasets, and missing methodological alignment as critical open issues and formulate 12 recommendations for research. Whereas transparency, data source diversity, conceptual rigor, label-set consolidation, inter-annotator agreement, and model validation on existing datasets warrant more attention, multi-label tasks related to criminal relevance, enhancing robustness through ensembling, and exploring performance gains through large foundation models represent promising avenues for future work.
- 7 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (6) , 1-39
Open AccessA Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in English
The dissemination of online hate speech can have serious negative consequences for individuals, online communities, and entire societies. This and the large volume of hateful online content prompted both practitioners’, e.g., in content moderation or law enforcement and researchers’ interest in machine learning models to automatically classify instances of hate speech. Whereas most scientific works address hate speech classification as a binary task, practice often requires a differentiation into sub-types, e.g., according to target, severity, or legality, which may overlap for individual content. Hence, researchers created datasets and machine learning models that approach hate speech classification in textual data as a multi-label problem. This work presents the first systematic and comprehensive survey of scientific literature on this emerging research landscape in English (N = 46). We contribute with a concise overview of 28 datasets suited for training multi-label classification models, revealing significant heterogeneity regarding label-set, size, meta-concept, annotation process, and inter-annotator agreement. Our analysis of 24 publications proposing suitable classification models further establishes inconsistency in evaluation and a preference for architectures based on Bidirectional Encoder Representation from Transformers (BERT) and Recurrent Neural Networks (RNNs). We identify imbalanced training data, reliance on crowdsourcing platforms, small and sparse datasets, and missing methodological alignment as critical open issues and formulate 12 recommendations for research. Whereas transparency, data source diversity, conceptual rigor, label-set consolidation, inter-annotator agreement, and model validation on existing datasets warrant more attention, multi-label tasks related to criminal relevance, enhancing robustness through ensembling, and exploring performance gains through large foundation models represent promising avenues for future work.
- 9 August 2025
- Published by Springer Nature
- p. 139-155
Reducing Information Overload: Because Even Security Experts Need to Blink
- 9 August 2025
- Published by Springer Nature
- p. 139-155
Reducing Information Overload: Because Even Security Experts Need to Blink
- Open Access
Bandit on the Hunt: Dynamic Crawling for Cyber Threat Intelligence
Public information contains valuable Cyber Threat Intelligence (CTI) that is used to prevent future attacks. While standards exist for sharing this information, much appears in non-standardized news articles or blogs. Monitoring online sources for threats is time-consuming and source selection is uncertain. Current research focuses on extracting Indicators of Compromise from known sources, rarely addressing new source identification. This paper proposes a CTI-focused crawler using multi-armed bandit (MAB) and various crawling strategies. It employs SBERT to identify relevant documents while dynamically adapting its crawling path. Our system ThreatCrawl achieves a harvest rate exceeding 25% and expands its seed by over 300% while maintaining topical focus. Additionally, the crawler identifies previously unknown but highly relevant overview pages, datasets, and domains.
Open AccessBandit on the Hunt: Dynamic Crawling for Cyber Threat Intelligence
Public information contains valuable Cyber Threat Intelligence (CTI) that is used to prevent future attacks. While standards exist for sharing this information, much appears in non-standardized news articles or blogs. Monitoring online sources for threats is time-consuming and source selection is uncertain. Current research focuses on extracting Indicators of Compromise from known sources, rarely addressing new source identification. This paper proposes a CTI-focused crawler using multi-armed bandit (MAB) and various crawling strategies. It employs SBERT to identify relevant documents while dynamically adapting its crawling path. Our system ThreatCrawl achieves a harvest rate exceeding 25% and expands its seed by over 300% while maintaining topical focus. Additionally, the crawler identifies previously unknown but highly relevant overview pages, datasets, and domains.
- Open Access
- 16 April 2025
- Published by Qeios Ltd
Review of: "SampleLLM: Optimizing Tabular Data Synthesis in Recommendations"
The study “SampleLLM: Optimizing Tabular Data Synthesis in Recommendations" proposes a novel method for tabular data synthesis with an emphasis on recommendations. SampleLLM consists of using an LLM for data generation and clustering, as well as a fe...
- 16 April 2025
- Published by Qeios Ltd
Open AccessReview of: "SampleLLM: Optimizing Tabular Data Synthesis in Recommendations"
The study “SampleLLM: Optimizing Tabular Data Synthesis in Recommendations" proposes a novel method for tabular data synthesis with an emphasis on recommendations. SampleLLM consists of using an LLM for data generation and clustering, as well as a fe...
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-16
‘We Do Not Have the Capacity to Monitor All Media’: A Design Case Study on Cyber Situational Awareness in Computer Emergency Response Teams
Computer Emergency Response Teams (CERTs) provide advisory, preventive and reactive cybersecurity services for authorities, citizens, and businesses. However, their responsibility of monitoring, analyzing, and communicating cyber threats have become challenging due to the growing volume and varying quality of information disseminated through public channels. Based on a design case study conducted from 2021 to 2023, this paper combines three iterations of expert interviews, design workshops and cognitive walkthroughs to design an automated, cross-platform and real-time cybersecurity dashboard. By adopting the notion of cyber situational awareness, the study extracts user requirements and design heuristics for enhanced threat awareness and mission awareness in CERTs, discussing the aspects of source integration, data management, customizable visualization, relationship awareness, information assessment, software integration, (inter-)organizational collaboration, and communication of stakeholder warnings.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open Access‘We Do Not Have the Capacity to Monitor All Media’: A Design Case Study on Cyber Situational Awareness in Computer Emergency Response Teams
Computer Emergency Response Teams (CERTs) provide advisory, preventive and reactive cybersecurity services for authorities, citizens, and businesses. However, their responsibility of monitoring, analyzing, and communicating cyber threats have become challenging due to the growing volume and varying quality of information disseminated through public channels. Based on a design case study conducted from 2021 to 2023, this paper combines three iterations of expert interviews, design workshops and cognitive walkthroughs to design an automated, cross-platform and real-time cybersecurity dashboard. By adopting the notion of cyber situational awareness, the study extracts user requirements and design heuristics for enhanced threat awareness and mission awareness in CERTs, discussing the aspects of source integration, data management, customizable visualization, relationship awareness, information assessment, software integration, (inter-)organizational collaboration, and communication of stakeholder warnings.
- Top Cited PapersOpen Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Privacy and Security
- Vol. 27 (2) , 1-20
CySecBERT : A Domain-Adapted Language Model for the Cybersecurity Domain
The field of cysec is evolving fast. Security professionals are in need of intelligence on past, current and —ideally — upcoming threats, because attacks are becoming more advanced and are increasingly targeting larger and more complex systems. Since the processing and analysis of such large amounts of information cannot be addressed manually, cysec experts rely on machine learning techniques. In the textual domain, pre-trained language models such as Bidirectional Encoder Representations from Transformers (BERT) have proven to be helpful as they provide a good baseline for further fine-tuning. However, due to the domain-knowledge and the many technical terms in cysec, general language models might miss the gist of textual information. For this reason, we create a high-quality dataset 1 and present a language model 2 specifically tailored to the cysec domain that can serve as a basic building block for cybersecurity systems. The model is compared on 15 tasks: Domain-dependent extrinsic tasks for measuring the performance on specific problems, intrinsic tasks for measuring the performance of the internal representations of the model, as well as general tasks from the SuperGLUE benchmark. The results of the intrinsic tasks show that our model improves the internal representation space of domain words compared with the other models. The extrinsic, domain-dependent tasks, consisting of sequence tagging and classification, show that the model performs best in cybersecurity scenarios. In addition, we pay special attention to the choice of hyperparameters against catastrophic forgetting, as pre-trained models tend to forget the original knowledge during further training.
- 8 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Privacy and Security
- Vol. 27 (2) , 1-20
Top Cited PapersOpen AccessCySecBERT : A Domain-Adapted Language Model for the Cybersecurity Domain
The field of cysec is evolving fast. Security professionals are in need of intelligence on past, current and —ideally — upcoming threats, because attacks are becoming more advanced and are increasingly targeting larger and more complex systems. Since the processing and analysis of such large amounts of information cannot be addressed manually, cysec experts rely on machine learning techniques. In the textual domain, pre-trained language models such as Bidirectional Encoder Representations from Transformers (BERT) have proven to be helpful as they provide a good baseline for further fine-tuning. However, due to the domain-knowledge and the many technical terms in cysec, general language models might miss the gist of textual information. For this reason, we create a high-quality dataset 1 and present a language model 2 specifically tailored to the cysec domain that can serve as a basic building block for cybersecurity systems. The model is compared on 15 tasks: Domain-dependent extrinsic tasks for measuring the performance on specific problems, intrinsic tasks for measuring the performance of the internal representations of the model, as well as general tasks from the SuperGLUE benchmark. The results of the intrinsic tasks show that our model improves the internal representation space of domain words compared with the other models. The extrinsic, domain-dependent tasks, consisting of sequence tagging and classification, show that the model performs best in cybersecurity scenarios. In addition, we pay special attention to the choice of hyperparameters against catastrophic forgetting, as pre-trained models tend to forget the original knowledge during further training.
- 18 August 2023
- Published by Elsevier in Computers & Security
- Vol. 134
Multi-level fine-tuning, data augmentation, and few-shot learning for specialized cyber threat intelligence
- 18 August 2023
- Published by Elsevier in Computers & Security
- Vol. 134
Multi-level fine-tuning, data augmentation, and few-shot learning for specialized cyber threat intelligence
- Top Cited PapersOpen Access
- 15 December 2022
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 55 (7) , 1-39
A Survey on Data Augmentation for Text Classification
Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization capabilities, it can also address many other challenges and problems, from overcoming a limited amount of training data to regularizing the objective, to limiting the amount of data used to protect privacy. Based on a precise description of the goals and applications of data augmentation and a taxonomy for existing works, this survey is concerned with data augmentation methods for textual classification and aims at providing a concise and comprehensive overview for researchers and practitioners. Derived from the taxonomy, we divide more than 100 methods into 12 different groupings and give state-of-the-art references expounding which methods are highly promising by relating them to each other. Finally, research perspectives that may constitute a building block for future work are provided.
- 15 December 2022
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 55 (7) , 1-39
Top Cited PapersOpen AccessA Survey on Data Augmentation for Text Classification
Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization capabilities, it can also address many other challenges and problems, from overcoming a limited amount of training data to regularizing the objective, to limiting the amount of data used to protect privacy. Based on a precise description of the goals and applications of data augmentation and a taxonomy for existing works, this survey is concerned with data augmentation methods for textual classification and aims at providing a concise and comprehensive overview for researchers and practitioners. Derived from the taxonomy, we divide more than 100 methods into 12 different groupings and give state-of-the-art references expounding which methods are highly promising by relating them to each other. Finally, research perspectives that may constitute a building block for future work are provided.
- Top Cited PapersOpen Access
- 12 April 2022
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 14 (1) , 135-150
Data augmentation in natural language processing: a novel text generation approach for long and short text classifiers
In many cases of machine learning, research suggests that the development of training data might have a higher relevance than the choice and modelling of classifiers themselves. Thus, data augmentation methods have been developed to improve classifiers by artificially created training data. In NLP, there is the challenge of establishing universal rules for text transformations which provide new linguistic patterns. In this paper, we present and evaluate a text generation method suitable to increase the performance of classifiers for long and short texts. We achieved promising improvements when evaluating short as well as long text tasks with the enhancement by our text generation method. Especially with regard to small data analytics, additive accuracy gains of up to 15.53% and 3.56% are achieved within a constructed low data regime, compared to the no augmentation baseline and another data augmentation technique. As the current track of these constructed regimes is not universally applicable, we also show major improvements in several real world low data tasks (up to +4.84 F1-score). Since we are evaluating the method from many perspectives (in total 11 datasets), we also observe situations where the method might not be suitable. We discuss implications and patterns for the successful application of our approach on different types of datasets.
- 12 April 2022
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 14 (1) , 135-150
Top Cited PapersOpen AccessData augmentation in natural language processing: a novel text generation approach for long and short text classifiers
In many cases of machine learning, research suggests that the development of training data might have a higher relevance than the choice and modelling of classifiers themselves. Thus, data augmentation methods have been developed to improve classifiers by artificially created training data. In NLP, there is the challenge of establishing universal rules for text transformations which provide new linguistic patterns. In this paper, we present and evaluate a text generation method suitable to increase the performance of classifiers for long and short texts. We achieved promising improvements when evaluating short as well as long text tasks with the enhancement by our text generation method. Especially with regard to small data analytics, additive accuracy gains of up to 15.53% and 3.56% are achieved within a constructed low data regime, compared to the no augmentation baseline and another data augmentation technique. As the current track of these constructed regimes is not universally applicable, we also show major improvements in several real world low data tasks (up to +4.84 F1-score). Since we are evaluating the method from many perspectives (in total 11 datasets), we also observe situations where the method might not be suitable. We discuss implications and patterns for the successful application of our approach on different types of datasets.
- 17 September 2021
- Published by Springer Nature
- p. 429-446
CySecAlert: An Alert Generation System for Cyber Security Events Using Open Source Intelligence Data
- 17 September 2021
- Published by Springer Nature
- p. 429-446
CySecAlert: An Alert Generation System for Cyber Security Events Using Open Source Intelligence Data