Spelling suggestions: "subject:"large scale etworks"" "subject:"large scale enetworks""
11 |
Community Detection of Anomaly in Large-Scale Network Dissertation - Adefolarin Bolaji .pdfAdefolarin Alaba Bolaji (10723926) 29 April 2021 (has links)
<p>The
detection of anomalies in real-world networks is applicable in different
domains; the application includes, but is not limited to, credit card fraud
detection, malware identification and classification, cancer detection from
diagnostic reports, abnormal traffic detection, identification of fake media
posts, and the like. Many ongoing and current researches are providing tools
for analyzing labeled and unlabeled data; however, the challenges of finding
anomalies and patterns in large-scale datasets still exist because of rapid
changes in the threat landscape. </p><p>In this study, I implemented a
novel and robust solution that combines data science and cybersecurity to solve
complex network security problems. I used Long Short-Term Memory (LSTM) model, Louvain
algorithm, and PageRank algorithm to identify and group anomalies in large-scale
real-world networks. The network has billions of packets. The developed model
used different visualization techniques to provide further insight into how the
anomalies in the network are related. </p><p>Mean absolute error (MAE) and root mean square error (RMSE) was used to validate the anomaly detection models, the
results obtained for both are 5.1813e-04
and 1e-03 respectively. The low loss from the training
phase confirmed the low RMSE at loss: 5.1812e-04, mean absolute error:
5.1813e-04, validation loss: 3.9858e-04, validation mean absolute error:
3.9858e-04. The result from the community detection
shows an overall modularity value of 0.914 which is proof of the existence of
very strong communities among the anomalies. The largest sub-community of the
anomalies connects 10.42% of the total nodes of the anomalies. </p><p>The broader aim and impact of this study was to provide
sophisticated, AI-assisted countermeasures to cyber-threats in large-scale
networks. To close the existing gaps created by the shortage of skilled and
experienced cybersecurity specialists and analysts in the cybersecurity field,
solutions based on out-of-the-box thinking are inevitable; this research was aimed
at yielding one of such solutions. It was built to detect specific and
collaborating threat actors in large networks and to help speed up how the
activities of anomalies in any given large-scale network can be curtailed in
time.</p><div><div><div>
</div>
</div>
</div>
<br>
|
12 |
On performance limitations of large-scale networks with distributed feedback controlTegling, Emma January 2016 (has links)
We address the question of performance of large-scale networks with distributed feedback control. We consider networked dynamical systems with single and double integrator dynamics, subject to distributed disturbances. We focus on two types of problems. First, we consider problems modeled over regular lattice structures. Here, we treat consensus and vehicular formation problems and evaluate performance in terms of measures of “global order”, which capture the notion of network coherence. Second, we consider electric power networks, which we treat as dynamical systems modeled over general graphs. Here, we evaluate performance in terms of the resistive power losses that are incurred in maintaining network synchrony. These losses are associated with transient power flows that are a consequence of “local disorder” caused by lack of synchrony. In both cases, we characterize fundamental limitations to performance as networks become large. Previous studies have shown that such limitations hold for coherence in networks with regular lattice structures. These imply that connections in 3 spatial dimensions are necessary to achieve full coherence, when the controller uses static feedback from relative measurements in a local neighborhood. We show that these limitations remain valid also with dynamic feedback, where each controller has an internal memory state. However, if the controller can access certain absolute state information, dynamic feedback can improve performance compared to static feedback, allowing also 1-dimensional formations to be fully coherent. For electric power networks, we show that the transient power losses grow unboundedly with network size. However, in contrast to previous results, performance does not improve with increased network connectivity. We also show that a certain type of distributed dynamic feedback controller can improve performance by reducing losses, but that their scaling with network size remains an important limitation. / <p>QC 20160504</p>
|
Page generated in 0.0518 seconds