Self-Supervised and Interpretable Anomaly Detection using Network Transformers

Marino, Daniel L.; Wickramasinghe, Chathurika S.; Rieger, Craig; Manic, Milos

doi:10.48550/arxiv.2202.12997

Cited by 2 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, some new attacks may be misclassified and regarded as false positives in investigations. • Interpretability: Previous works have tended to focus on sample classification, which lacks semantic interpretability [21].…”

Section: Related Workmentioning

confidence: 99%

Hybrid cyber threats detection using explainable AI in Industrial IoT

Liu,

2023

2023 International Conference on Human-Centered Cognitive Systems (HCCS)

View full text Add to dashboard Cite

The rise of new technologies has enabled the combination of multiple cyber threats to become more sophisticated and capable cyber attacks, which can result in significant losses and consequences. This work aims to develop a hybrid threat detection system using explainable artificial intelligence techniques, preventing the growing number of combined cyber-attacks in IoT environments. A multilayer hybrid cyber threats model was proposed to analyse increasingly complicated and capable cyber attacks. In addition, an explainable artificial intelligence (XAI) model was designed to create an understandable interpretation for the detection model. The experimental results demonstrate the effectiveness of the proposed hybrid cyber threats analysis model and XAI model.

show abstract

Section: Related Workmentioning

confidence: 99%

Hybrid cyber threats detection using explainable AI in Industrial IoT

Liu,

2023

2023 International Conference on Human-Centered Cognitive Systems (HCCS)

View full text Add to dashboard Cite

show abstract

“…Using transformers for cybersecurity and malicious software detection (Rahali et al, 2021) Tactic 8: Source code as a set of features Self-supervised and interpretable anomaly detection using network transformers (Marino et al, 2022) Tactic 9: Network transformer (NeT) An Accuracy-Maximization Approach for Claims Classifiers in Document Content Analytics for Cybersecurity (Ameri et al, 2022) Tactic 10: ClaimsBert Towards the evolutionary assessment of neural transformers trained on source code (Kanade et al, 2020) Learning and evaluating contextual embedding of source code Tactic 11: Code Understanding BERT (CuBERT) Attack Tactic Identification by Transfer Learning of Language Model Tactic 12: Packet embedding method-based language model (PELAT) 13…”

Section: Problem Statementmentioning

confidence: 99%

“…8.9.3.9 Tactic 9: Network Transformer (NeT) (Marino et al 2022) Table 8.12: Tactic 9 Network Transformer (NeT) (Marino et al 2022) The human-readable documents are complicated for automation due to their formats and the natural language structure…”

Section: Design Diagram N/amentioning

confidence: 99%

Cybersecurity design of data-intensive systems

Avcı

View full text Add to dashboard Cite

Research method has a critical role within the empirical studies. In order to converge valid and reliable outcomes, clear cut research methodologies should be applied and reported in the selected primary studies. The types of the research methods can be listed as "Case Study" (in depth investigation with a real-life context), "Experiment" (scientific procedure to test a hypothesis) and "Short Example". It can be derived from Table 5.5 that there is not a tendency towards a research method, considering the fact that the gap between the percentages of the methodologies is not wide. Nevertheless, experimentation is used more often comparing to case studies and short examples to evaluate the system architectures.

show abstract

Self-Supervised and Interpretable Anomaly Detection using Network Transformers

Cited by 2 publications

References 27 publications

Hybrid cyber threats detection using explainable AI in Industrial IoT

Hybrid cyber threats detection using explainable AI in Industrial IoT

Cybersecurity design of data-intensive systems

Contact Info

Product

Resources

About