A Comprehensive Survey of Databases and Deep Learning Methods for Cybersecurity and Intrusion Detection Systems

Gumusbas, Dilara; Yldrm, Tulay; Genovese, Angelo; Scotti, Fabio

doi:10.1109/jsyst.2020.2992966

Cited by 94 publications

(41 citation statements)

References 96 publications

(112 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the other 97% of attempts are social engineering-driven. These red flags mean additional fortification of data security, application security on-device security and network security only safeguards a small minority of attacks, regardless of the operating system and types of machines [6].…”

Section: Human Factor and Social Engineering Landscapementioning

confidence: 99%

Social Engineering Attack Classifications on Social Media Using Deep燣earning

Aun¹,

Gan²,

Wahab³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In defense-in-depth, humans have always been the weakest link in cybersecurity. However, unlike common threats, social engineering poses vulnerabilities not directly quantifiable in penetration testing. Most skilled social engineers trick users into giving up information voluntarily through attacks like phishing and adware. Social Engineering (SE) in social media is structurally similar to regular posts but contains malicious intrinsic meaning within the sentence semantic. In this paper, a novel SE model is trained using a Recurrent Neural Network Long Short Term Memory (RNN-LSTM) to identify well-disguised SE threats in social media posts. We use a custom dataset crawled from hundreds of corporate and personal Facebook posts. First, the social engineering attack detection pipeline (SEAD) is designed to filter out social posts with malicious intents using domain heuristics. Next, each social media post is tokenized into sentences and then analyzed with a sentiment analyzer before being labelled as an anomaly or normal training data. Then, we train an RNN-LSTM model to detect five types of social engineering attacks that potentially contain signs of information gathering. The experimental result showed that the Social Engineering Attack (SEA) model achieves 0.84 in classification precision and 0.81 in recall compared to the ground truth labeled by network experts. The experimental results showed that the semantics and linguistics similarities are an effective indicator for early detection of SEA.

show abstract

Section: Human Factor and Social Engineering Landscapementioning

confidence: 99%

Social Engineering Attack Classifications on Social Media Using Deep燣earning

Aun¹,

Gan²,

Wahab³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…It provides a detailed classification of intrusion detection value for each emerging technology. D. Gumusbas et al, (2021): [15] The authors proposed to provide a road map for readers who wish to understand the potential of DL methods in network security and intrusion detection systems. Also, analysis of benchmark datasets is used in the literature to train DL models.…”

Section: Literature Surveymentioning

confidence: 99%

Cyber Security System Based on Machine Learning Using Logistic Decision Support Vector

Hemanand²,

Vallem³

2023

MJCS

View full text Add to dashboard Cite

Nowadays, we are moving towards cybersecurity against digital attacks to protect systems, networks, and data in developing areas. A collection of technologies and processes is at the core of cybersecurity. A network security system is a feature of network and computer (host) security. Cybercrime leads to billion-dollar losses. Given these crimes, the security of computer systems has become essential to reduce and avoid the impact of cybercrime. We propose the Logistics Decision Support Vector (LDSV) algorithm dealing with this problem. Initially, we collected the KDD Cup 99 dataset to create a network intrusion detection, such as penetrations or attacks, a prognosis model that varies between the "Non Malicious" and "Malicious" standard links. These method finds the cyber-attack category based on the behavior features. In the second step, data preprocessing should be cleaned from errors, and raw data should be converted into a prepared dataset. The third step is Feature Selection (FS) techniques often improve the feature selection process in an Intrusion Detection System (IDS) that is more convenient for using the mean of the Chi-square test (MAC) method. Finally, a classification is done to classify and detect the network intrusion detection based on LDSV for Cyber security. The proposed LDSV simulation is based on the Precision F-Measure, Recall, and Accuracy for the best result.

show abstract

“…This dataset is also called CSE‐CIC‐IDS2018 it was created in collaboration with by Communications Security Establishment (CSE) and the Canadian Institute for Cybersecurity (CIC) in the year 2018 (Leevy & Khoshgoftaar, 2020), this dataset contains 83 features (Rios et al, 2020). This dataset is collected from two different capturing methods for testing and training from the database, full packet network traffic and reduced packet network traffic along with system logs are two different data collection procedures (Gumusbas et al, 2020). The dataset contains the following attack types in the network Brute‐force, DoS, DDoS, Web attacks, Heartbleed, Botnet, and infiltration (CSE‐CIC‐IDS2018, 2021; Lee et al, 2020; Sharafaldin et al, 2018).…”

Section: Benchmark Datasetmentioning

confidence: 99%

Network intrusion detection system: A survey on artificial intelligence‐based techniques

Habeeb

Babu²

2022

Expert Systems

View full text Add to dashboard Cite

High data rate requirements in recent years have resulted in the massive expansion of communication systems, network size and the amount of data generated and processed. This has eventually caused many threats to the communication networks as well due to a more frequent generation of security attacks that are either novel or the mutation of the existing attacks. To secure the networks against such threats, an intrusion detection system (IDS) is considered as one of the promising solutions. The main problem with the IDS is its increased false alarm rate (FAR) in detecting the zero‐day attacks. To improve the detection accuracy and minimizing the FAR, the researchers proposed IDS solutions using artificial intelligence (AI) approaches. In this research, we have systematically reviewed the recent AI‐based network IDS (NIDS) solutions proposed during the period 2016–2021 by the research community. We systematically analysed the proposed NIDS solutions based on their strengths, shortcomings, AI methodology adopted, datasets, and the evaluation metrics used for evaluation purposes. From the review, we observed that the hybrid approach is mostly adopted by the researchers to propose AI‐based NIDS solutions, with a trend shifting to deep learning‐based approaches over the last 2 years. Also, most of the proposed solutions are evaluated using a very old dataset with only a few studies opting for the latest datasets. Finally based on our observations, we highlighted the research challenges and the future research directions to help young researchers to contribute to this field.

show abstract

A Comprehensive Survey of Databases and Deep Learning Methods for Cybersecurity and Intrusion Detection Systems

Cited by 94 publications

References 96 publications

Social Engineering Attack Classifications on Social Media Using Deep燣earning

Social Engineering Attack Classifications on Social Media Using Deep燣earning

Cyber Security System Based on Machine Learning Using Logistic Decision Support Vector

Network intrusion detection system: A survey on artificial intelligence‐based techniques

Contact Info

Product

Resources

About