Contemporary survey on effectiveness of machine and deep learning techniques for cyber security

Suresh, P.; Logeswaran, K.; Keerthika, P.; Devi, R. Manjula; Sentamilselvan, K.; Kamalam, G. K.; Muthukrishnan, H.

doi:10.1016/b978-0-323-85209-8.00007-9

Cited by 20 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our findings underscored the critical need for human oversight in AI-driven cybersecurity solutions [9], [2], [59]. The occurrence of hallucinations and the variability in LLM performance in different scenarios highlight the limitations of AI in fully understanding the nuances of human communication and decision-making in complex situations [45], [1]. Human oversight in AI-driven ransomware negotiations can provide several benefits [10], [15].…”

Section: A the Need For Human Oversightmentioning

confidence: 74%

Evaluating Large Language Models in Ransomware Negotiation: A Comparative Analysis of ChatGPT and Claude

Kumamoto,

Yoshida,

Fujima

2023

Preprint

View full text Add to dashboard Cite

This study presents a comprehensive analysis of the application of Large Language Models (LLMs), specifically ChatGPT and Claude, in the context of ransomware negotiation. Ransomware, an increasingly prevalent and sophisticated cyber threat, necessitates innovative response strategies. This study examines the capabilities of these LLMs in simulating human-like negotiation tactics against ransomware attacks, focusing on two main types: cryptographic and data exfiltration ransomware. Through a series of controlled simulations, the efficacy of ChatGPT and Claude in understanding complex language constructs, formulating negotiation strategies, and their adaptability to varying ransomware scenarios is evaluated. The research highlights the strengths of these models in response accuracy, adaptability, and psychological manipulation resistance. However, it also reveals their susceptibility to producing hallucinations — instances of unrealistic or inaccurate responses. The study contributes to the understanding of AI's potential in cybersecurity, emphasizing the need for improvements in AI reliability, ethical considerations, and the integration of human oversight. The findings suggest that while LLMs hold promising potential in enhancing cyber defense mechanisms, their deployment in high-stakes scenarios like ransomware negotiations must be approached with caution and continuous oversight.

show abstract

Section: A the Need For Human Oversightmentioning

confidence: 74%

Evaluating Large Language Models in Ransomware Negotiation: A Comparative Analysis of ChatGPT and Claude

Kumamoto,

Yoshida,

Fujima

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Parallel processing and deep learning techniques are preferred in processing these data given their high speed and accuracy. Deep learning techniques have also been used in recent years to detect malware [72][73][74]. Malicious programs have many characteristics that can affect systems by modifying their data.…”

Section: Deep Learning In Cybersecuritymentioning

confidence: 99%

The Significance of Machine Learning and Deep Learning Techniques in Cybersecurity: A Comprehensive Review

2023

ijcsm

View full text Add to dashboard Cite

People in the modern era spend most of their lives in virtual environments that offer a range of public and private services and social platforms. Therefore, these environments need to be protected from cyber attackers that can steal data or disrupt systems. Cybersecurity refers to a collection of technical, organizational, and executive means for preventing the unauthorized use or misuse of electronic information and communication systems to ensure the continuity of their work, guarantee the confidentiality and privacy of personal data, and protect consumers from threats and intrusions. Accordingly, this article explores the cybersecurity practices that protect computer systems from attacks, hacking, and data thefts and investigates the role of artificial intelligence in this domain. This article also summarizes the most significant literature that explore the roles and effects of machine learning and deep learning techniques in cybersecurity. Results show that machine learning and deep learning techniques play significant roles in protecting computer systems from unauthorized entry and in controlling system penetration by predicting and understanding the behaviour and traffic of malicious software.

show abstract

“…Upon detection of an intrusive activity, the Intrusion Detection System (IDS) reports the intrusion to a SIEM (Security Information and Event Management) system where determination of valid threats is carried out amidst every other alarm, false or not [117. However, with much time spent in threat determination, there is a window for more damage to be perpetrated on the system or network because whereas IDSs are instrumental in network monitoring, the significance of their implementation relies on what is done with the information they generate, which means that they do not necessarily resolve security issues hence cannot add security layers unless appropriate policies to stop the identified threats are administered [118].…”

Section: Common Non-artificial Intelligence Based Techniquesmentioning

confidence: 99%

Assessment of existing cyber-attack detection models for web-based systems

Awuor¹

2023

Global J. Eng. Technol. Adv.

View full text Add to dashboard Cite

In the current technological environment, different entities engage in intricate cyber security approaches in order to counter damages and disruptions in web-based systems. The design of the security protocols relies on the guarantee that attacks are prevented in the web-based systems. Prevention and detection using techniques such as access control tools, encryption and firewalls present limitations in the full protection of web-based systems. Furthermore, despite the sophistication of current systems, there are still shortfalls in high false positive and false negative threat detection rates, which is attributed to poor adaptation by systems and networks to the changing threats and behavior of cyber-criminals. In this perspective, this survey paper discusses the existing cyber-attack detection models, and recommends the cyber-attack detection models and techniques that are appropriate for web-based systems. It is evident that deep learning techniques offer better performance and robustness compared to traditional machine learning techniques and other non-artificial intelligence-based techniques. Deep learning techniques learn and extract features automatically without human intervention and can also handle big and multidimensional data more conventionally than the other techniques.

show abstract

Contemporary survey on effectiveness of machine and deep learning techniques for cyber security

Cited by 20 publications

References 19 publications

Evaluating Large Language Models in Ransomware Negotiation: A Comparative Analysis of ChatGPT and Claude

Evaluating Large Language Models in Ransomware Negotiation: A Comparative Analysis of ChatGPT and Claude

The Significance of Machine Learning and Deep Learning Techniques in Cybersecurity: A Comprehensive Review

Assessment of existing cyber-attack detection models for web-based systems

Contact Info

Product

Resources

About