This paper presents the FlowTransformer framework, a novel approach for implementing transformer-based Network Intrusion Detection Systems (NIDSs). FlowTransformer leverages the strengths of transformer models in identifying the long-term behaviour and characteristics of networks, which are often overlooked by most existing NIDSs. By capturing these complex patterns in network traffic, FlowTransformer offers a flexible and efficient tool for researchers and practitioners in the cybersecurity community who are seeking to implement NIDSs using transformer-based models. FlowTransformer allows the direct substitution of various transformer components, including the input encoding, transformer, classification head, and the evaluation of these across any flow-based network dataset. To demonstrate the effectiveness and efficiency of the FlowTransformer framework, we utilise it to provide an extensive evaluation of various common transformer architectures, such as GPT 2.0 and BERT, on three commonly used public NIDS benchmark datasets. We provide results for accuracy, model size and speed. A key finding of our evaluation is that the choice of classification head has the most significant impact on the model performance. Surprisingly, Global Average Pooling, which is commonly used in text classification, performs very poorly in the context of NIDS. In addition, we show that model size can be reduced by over 50\%, and inference and training times improved, with no loss of accuracy, by making specific choices of input encoding and classification head instead of other commonly used alternatives.
FedSecureFormer: A Fast, Federated and Secure Transformer Framework for Lightweight Intrusion Detection in Connected and Autonomous Vehicles
Department of Computer Science and Information Systems, BITS Pilani, Pilani Campus（计算机科学与信息系统系，比斯汉学院）；Department of Systems and Computer Engineering, Carleton University（系统与计算机工程系，卡尔顿大学）
A Novel Unified Lightweight Temporal-Spatial Transformer Approach for Intrusion Detection in Drone Networks
Department of Computer Science and Engineering, Jahangirnagar University（贾杭吉纳大学计算机科学与工程系）；Department of Computer Science and Engineering, Bangladesh Army University of Science & Technology（孟加拉国陆军科学技术大学计算机科学与工程系）；State University of Bangladesh, Department of Computer Science and Engineering（孟加拉国国立大学计算机科学与工程系）；Skill Morph Research Lab., Skill Morph（Skill Morph研究实验室）
Self-Supervised Transformer-based Contrastive Learning for Intrusion Detection Systems
Dept. of Electrical and Computer Engineering, University of Thessaly（电气与计算机工程系，希腊塞萨洛尼基大学）；Centre for Research and Technology Hellas, CERTH（希腊研究中心与技术中心，CERTH）
ExAI5G: A Logic-Based Explainable AI Framework for Intrusion Detection in 5G Networks
organization= Faculty of Information Technology；Electrical Engineering, University of Oulu , addressline= , city= Oulu , postcode= 90570 , state= , country= Finland
SE-Enhanced ViT and BiLSTM-Based Intrusion Detection for Secure IIoT and IoMT Environments
LSEA Lab., Faculty of Technology University of MEDEA Medea 26000, Algeria；LSEA Lab, Faculty of Science University of MEDEA Medea 26000, Algeria；Department of Computer Engineering Gazi University Ankara, Turkey；Department of Management Information Systems Gazi University Ankara, Turkey
BARTPredict: Empowering IoT Security with LLM-Driven Cyber Threat Prediction
Badji Mokhtar-Annaba University（巴吉·穆克塔尔-安纳巴大学）；University of La Rochelle（拉罗谢尔大学）；National Higher School of Technology and Engineering -Annaba（安纳巴国家技术与工程高等学校）
A Transformer-Based Framework for Payload Malware Detection and Classification
University of West Florida（西佛罗里达大学）；Florida Institute For Human and Machine Cognition (IHMC)（佛罗里达人机认知研究所）；Center for Cybersecurity, University of West Florida（西佛罗里达大学网络安全中心）
Data-Efficient Unknown Attack Detection in IoT Networks Using Pretrained Language Models
University of Ottawa（渥太华大学）；School of Electrical Engineering and Computer Science, University of Ottawa（渥太华大学电气与计算机工程学院）；Research Ireland Lero Centre, University of Limerick（利默里克大学爱尔兰研究Lero中心）
