A Review on the Effectiveness of Machine Learning and Deep Learning Algorithms for Cyber Security

Geetha, R.; Thilagam, T.

doi:10.1007/s11831-020-09478-2

Cited by 64 publications

(28 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Intrusion detection, malware detection, spam detection, and phishing detection are common areas that applied DL algorithms (FIGURE 6) [56]- [60].…”

Section: ) Classification By Application Areasmentioning

confidence: 99%

“…[65]. Malware has become a significant concern among cybersecurity experts in recent years; thus, having an effective and robust detection approach is crucial to handle rapidly evolved malware threats [60]. Malware detection methods can be categorized into two groups: PC-based and Android-based.…”

Section: ) Classification By Application Areasmentioning

confidence: 99%

“…Phishing detection is another domain in cybersecurity that DL proved to be an effective solution [58], [60], [69], [70]. Similar to spam, phishing can also be spread through several communication channels, such as email, SMS, website, online social network, etc.…”

Section: ) Classification By Application Areasmentioning

confidence: 99%

“…DL techniques can be classified into five categories: discriminative (supervised), generative (unsupervised), hybrid, ensemble, and reinforcement as illustrated in FIGURE 7 [22], [58], [60], [72], [73]. A list of abbreviations for various DL techniques is provided in TABLE 4.…”

Section: ) Classification By Techniquesmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning for Phishing Detection: Taxonomy, Current Challenges and Future Directions

Selamat

Krejcar

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Phishing has become an increasing concern and captured the attention of end-users as well as security experts. Despite decades of development and improvement, existing phishing detection techniques still suffer from the deficiency in performance accuracy and the inability to detect unknown attacks. Motivated to solve these problems, many researchers in the cybersecurity domain have shifted their attention to phishing detection that capitalizes on machine learning techniques. In recent years, deep learning has emerged as a branch of machine learning that has become a promising solution for phishing detection. As a result, this study proposes a taxonomy of deep learning algorithms for phishing detection by examining 81 selected papers using a systematic literature review approach. The paper first introduces the concept of phishing and deep learning in the context of cybersecurity. Then, phishing detection and deep learning algorithm taxonomies are provided to classify the existing literature into various categories. Next, taking the proposed taxonomy as a baseline, this study comprehensively reviews the state-of-the-art deep learning techniques and analyzes their advantages as well as disadvantages. Subsequently, the paper discusses various issues deep learning faces in phishing detection and proposes future research directions to overcome these challenges. Finally, an empirical analysis is conducted to evaluate the performance of various deep learning techniques in a practical context and highlight the related issues that motivate researchers in their future works. The results obtained from the empirical experiment showed that the common issues among most of the state-of-the-art deep learning algorithms are manual parameter-tuning, long training time, and deficient detection accuracy.

show abstract

“…Intrusion detection, malware detection, spam detection, and phishing detection are common areas that applied DL algorithms (FIGURE 6) [56]- [60].…”

Section: ) Classification By Application Areasmentioning

confidence: 99%

Section: ) Classification By Application Areasmentioning

confidence: 99%

Section: ) Classification By Application Areasmentioning

confidence: 99%

Section: ) Classification By Techniquesmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for Phishing Detection: Taxonomy, Current Challenges and Future Directions

Selamat

Krejcar

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Deep learning is the field of cybersecurity that is currently receiving the most attention. [16][17][18] As with deep neural networks (DNNs), this is constantly debated. DNNs are NNs with several hidden layers that are used as an instruction.…”

mentioning

confidence: 99%

Deep belief network and support vector machine fusion for distributed denial of service and economical denial of service attack detection in cloud

Dennis

Priya²

2021

Concurrency and Computation

View full text Add to dashboard Cite

Cloud computing is a progressive technology that offers computing resources as Internet-based services, revolutionized information, and communication technologies.From an economic standpoint, this transformation is beneficial because it allows them to streamline technology infrastructure and capital costs. However, economical denial of service (EDoS) potential is a crucial impediment to cloud computing success. Several improved ways to detect EDoS and distributed denial of service (DDoS) attacks in the cloud have been presented; nevertheless, these approaches still result in a considerable reduction in detection accuracy when employed in a cloud setting. Because selecting relevant features and precise classifiers for attack detection is a challenge.We recommend using an EDoS and DDoS attack identification framework in the cloud based on optimized deep learning techniques for higher detection accuracy. The experimental results reveal True Positive Rate (TPR) varies from 98.9% to 99.8% when using deep belief network with support vector machine as a learning mechanism, while True Negative Rate (TNR) from 99.6% to 99.9%. TPR and TNR were found to have average values of 99.32% and 99.67%, respectively. At 1600 requests/s, the maximum accuracy achieved and the overall accuracy of the proposed strategy was 99.78%. K E Y W O R D Sdeep belief network (DBN), distributed denial of service (DDoS), economical denial of service (EDoS), support vector machine (SVM) INTRODUCTIONCloud computing is currently widely regarded as the most cost-effective platform for delivering big data and artificial intelligence capabilities to businesses and cloud customers through the Internet. As a result, there is no need to invest in an extensive computer system because cloud computing delivers inexpensive and scalable on-demand system requirements. 1 In contrast to the commencement of the cloud computing era, which occurred shortly after the high-performance era; today's cloud computing has evolved into a significant associate for Internet of Things (IoT), big data analytics, and intelligence business solutions, in addition to its traditional fundamental facilities. 2However, in this new technology, security is a significant worry. 3 A denial of service (DoS) attack is a common challenge in cloud security. DoS assaults raise the load on the server and render the system unusable. Because of these security concerns, many clients are hesitant to use it for their business and other uses. 4 As a result, cloud computing's popularity has been hampered by security concerns. The network that interconnects the system in a cloud, for example, must be secure. Without a doubt, sharing your data and executing your software on someone else's hard drive can look to be hazardous, posing significant hazards to an organization's data. 5 Cloud computing allows an attacker attempting to extort money from

show abstract

Artificial Intelligence for Cybersecurity: Recent Advancements, Challenges and Opportunities

Rani

Kumar

Mittal

et al. 2022

Robotics and AI for Cybersecurity and Critical Infrastructure in Smart Cities

View full text Add to dashboard Cite

A Review on the Effectiveness of Machine Learning and Deep Learning Algorithms for Cyber Security

Cited by 64 publications

References 60 publications

Deep Learning for Phishing Detection: Taxonomy, Current Challenges and Future Directions

Deep Learning for Phishing Detection: Taxonomy, Current Challenges and Future Directions

Deep belief network and support vector machine fusion for distributed denial of service and economical denial of service attack detection in cloud

Artificial Intelligence for Cybersecurity: Recent Advancements, Challenges and Opportunities

Contact Info

Product

Resources

About