A New Intrusion Detection System Based on Fast Learning Network and Particle Swarm Optimization Article 2022

Running head: ARTICLE SUMMARY
Article Summary
Name of the Student:
Name of the University:
Author note:

1ARTICLE SUMMARY
A New Intrusion Detection System Based on Fast Learning Network and Particle Swarm
Optimization
Summary:
According to Ali, Al Mohammed, Ismail, and Zolkipli (2018), in the contemporary
technology driven society, the concern for the network security has increased. The attacks that
occur in the cyber world are much more capable than the current malware detection system. The
new intrusion detection system is the technology which makes use of the artificial neural
network based intrusion detection which allows it to learn real time attacks that has occurred into
the system. This reduces the false positives or the false negatives which might get detected by
the system and with the addition of the fast learning network or FLN, which is based upon
particle swarm optimization or PSO, the process gets much easier and quicker. Comparison has
been done with it and a lot of Meta heuristic algorithms and this technology have out-performed
them all. The paper also determines the various researches that has been conducted to understand
the system of intrusion detection. This was considered to be the initial purpose of the research,
using intrusion detection system to prevent cyber attacks and misuse of computers. This is
widely available in recent technology with a lot of variety, but all of them has some general
weaknesses or ineffectiveness with the lack of sufficient security as presented by the
commercially available system. This increases the need for the further research and development
of a better and a more dynamic system to detect intrusion. In order to make this successful the
system must identify all the intrusion attacks attempted or ongoing and work accordingly. All
these are discussed briefly in the paper.

2ARTICLE SUMMARY
Evolving support vector machines using whale optimization algorithm for spam profiles
detection on online social networks in different lingual contexts.
Summary:
In the contemporary era, one of the most challenging technical issues about the social
networking online is the detection of the SPAMs and Intrusions in profiles. As mentioned by
Ala’M, Faris, Alqatawna, and Hassonah (2018), these profiles are a big sources of bad and
unwanted advertisement which can not only lead to SPAMS but also generates malicious
activities, and cyber attacks. Hence in this research we understand the need for efficient and
accurate SPAM detection models ad also methods to remove them from the online social
networking websites. This research paper shows the development of a hybrid model based upon
the machine learning technology which based on the Whale Optimization Algorithm and Support
Vector Machine and has the purpose of identifying SPAMs on online social media. This model,
as discussed in the research can detect spammers using few of the most influential features of the
detection process like Automation and suggest appropriate measure. It has been tested for
different languages, mainly 4 of them which are English, Spanish, Arabic and Korean. This
model has proved that it is better than any others in terms of precision, accuracy and the
preventive measures suggestions. In this technology, Whale optimization Algorithm, allow it to
perform two tasks simultaneously. One of them is to optimize the SVM parameters and the other
one is the task of selection of the features. Application of this model in different languages have
shown some influential features like content based features, characteristics and behavioral
features and others which has been depicted and described as an effective SPAM detection
model in the research.

3ARTICLE SUMMARY
References:
Ala’M, A.-Z., Faris, H., Alqatawna, J. f., & Hassonah, M. A. (2018). Evolving support vector
machines using whale optimization algorithm for spam profiles detection on online social
networks in different lingual contexts. Knowledge-Based Systems, 153, 91-104.
Ali, M. H., Al Mohammed, B. A. D., Ismail, A., & Zolkipli, M. F. (2018). A new intrusion
detection system based on fast learning network and particle swarm optimization. IEEE
Access, 6, 20255-20261.