$Unsupervised Anomaly Detection in NSL-KDD Using $\beta$-VAE: A Latent Space and Reconstruction Error Approach$

Unsupervised Anomaly Detection in NSL-KDD Using $\beta$-VAE: A Latent Space and Reconstruction Error Approach

Ali Nemati6 days ago25 sec read2 views

The paper introduces an unsupervised method using $\beta$ -Variational Autoencoders to detect anomalies in network traffic on the NSL-KDD dataset, comparing distance measurements in latent space and reconstruction error metrics. This approach is significant for improving Intrusion Detection Systems as IT and OT integration grows, offering content creators tools to enhance cybersecurity through advanced unsupervised learning techniques.

Read the full article at arXiv stat.ML

Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.

Comments

Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning

Researchers have discovered a new type of backdoor attack on vertical federated learning systems that doesn't require triggers, posing significant pri...Researchers have discovered a new type of backdoor attack on vertical federated learning systems that doesn't require triggers, posing significant privacy risks even when attackers are only curious during training. This feature-based triggerless atta...

Ali Nemati

AI & Machine Learning6 days ago27 sec read

Advantage-based Temporal Attack in Reinforcement Learning

Researchers introduced Advantage-based Adversarial Transformer (AAT), a method to generate more effective temporal correlated adversarial examples for...Researchers introduced Advantage-based Adversarial Transformer (AAT), a method to generate more effective temporal correlated adversarial examples for DRL models by capturing dependencies across time steps using MSCSA and weighted advantage mechanism...

Ali Nemati

AI & Machine Learning6 days ago27 sec read

Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception

Researchers propose MVIG attack, a framework that uses mutual view information graph and temporal graph learning to adaptively exploit vulnerabilities...Researchers propose MVIG attack, a framework that uses mutual view information graph and temporal graph learning to adaptively exploit vulnerabilities in collaborative perception systems used by autonomous vehicles. This method significantly reduces ...

Ali Nemati

Cybersecurity6 days ago24 sec read

Malware Classification Leveraging NLP & Machine Learning for Enhanced Accuracy

Researchers have developed a new method using natural language processing and machine learning to classify malware more accurately by analyzing textua...Researchers have developed a new method using natural language processing and machine learning to classify malware more accurately by analyzing textual features through n-gram techniques. This approach significantly improves classification accuracy t...

Ali Nemati

Cybersecurity6 days ago28 sec read

Influence of Autoencoder Latent Space on Classifying IoT CoAP Attacks

A new study explores the use of autoencoder latent space combined with classification techniques to detect CoAP-based attacks in IoT environments. The...A new study explores the use of autoencoder latent space combined with classification techniques to detect CoAP-based attacks in IoT environments. The research demonstrates over 99% precision in identifying security breaches using just two learned fe...

Ali Nemati

Unsupervised Anomaly Detection in NSL-KDD Using $\beta$-VAE: A Latent Space and Reconstruction Error Approach

Related Articles

Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning

Advantage-based Temporal Attack in Reinforcement Learning

Learning Mutual View Information Graph for Adaptive Adversarial Collaborative Perception

Malware Classification Leveraging NLP & Machine Learning for Enhanced Accuracy

Influence of Autoencoder Latent Space on Classifying IoT CoAP Attacks