Applications in Security and Evasions in Machine Learning: A Survey

Sagar, Ramani; Jhaveri, Rutvij H.; Borrego, Carlos

doi:10.3390/electronics9010097

Cited by 52 publications

(29 citation statements)

References 141 publications

(142 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The studies [122], [123] investigated the security risks of traditional applications, and developed defence strategies to defend applications from various security risks. In a similar context, to realise the true potential of blockchain systems, the first step is to explore and clarify the security risks that could appear.…”

Section: A Motivationmentioning

confidence: 99%

Exploring Sybil and Double-Spending Risks in Blockchain Systems

Iqbal

Matulevičius

2021

IEEE Access

View full text Add to dashboard Cite

This paper is partially supported by the ERASMUS+ sectoral alliance program on A Blueprint for sectoral cooperation on blockchain skills and development (CHAISE), project code 621646-EPP-1-2020-1-FREPPK2-SSA-B. The European Commission support for the production of this publication does not constitute endorsement of the contents which reflects the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained therein.

show abstract

Section: A Motivationmentioning

confidence: 99%

Exploring Sybil and Double-Spending Risks in Blockchain Systems

Iqbal

Matulevičius

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…From previous research [12][13][14] and descriptions related to insider threat detection and analysis based on machine learning methodology, we selected the classification and clustering concepts as well as the related techniques [15,16] for anomaly detection and misuse as the main scope of this research.…”

Section: Insider Threats Based On Machine Learning Approachmentioning

confidence: 99%

Study on Inside Threats Based on Analytic Hierarchy Process

Seo

Kim

2020

Symmetry

View full text Add to dashboard Cite

Insider threats that occur within organizations cause more serious damage than external threats. However, there are many factors that are difficult to determine, such as the definition, classification, and severity of security breaches; hence, it is necessary to analyze system logs and user behavior-based scenarios within organizations. The reality is that qualitative judgment criteria are different for everyone to apply, and there is no detailed verification procedure to compare them objectively. In this study, realistic insider threats were examined through the definition, classification, and correlation/association analysis of various human–machine logs of acts associated with security breaches that occur in an organization. In addition, a quantitative process and decision-making tool were developed for insider threats by establishing various internal information leakage scenarios. As a result, insider threats were assessed quantitatively and a decision-making process was completed that enabled case analysis based on several insider threat scenarios. This study will enable precise modeling of insider threats that occur in real organizations and will support an objective process and a decision-making system to establish a range of required information for security protection measures.

show abstract

“…The usage of machine learning and artificial intelligence techniques is getting expanded rapidly in different areas of life such as finance [14][15][16], education [17], medicine [18][19][20][21], manufacturing industry [22], and particularly in the field of cyber security [23][24][25][26][27][28].…”

Section: Introductionmentioning

confidence: 99%

A Survey on Machine Learning Techniques for Cyber Security in the Last Decade

et al. 2020

View full text Add to dashboard Cite

Pervasive growth and usage of the Internet and mobile applications have expanded cyberspace. The cyberspace has become more vulnerable to automated and prolonged cyberattacks. Cyber security techniques provide enhancements in security measures to detect and react against cyberattacks. The previously used security systems are no longer sufficient because cybercriminals are smart enough to evade conventional security systems. Conventional security systems lack efficiency in detecting previously unseen and polymorphic security attacks. Machine learning (ML) techniques are playing a vital role in numerous applications of cyber security. However, despite the ongoing success, there are significant challenges in ensuring the trustworthiness of ML systems. There are incentivized malicious adversaries present in the cyberspace that are willing to game and exploit such ML vulnerabilities. This paper aims to provide a comprehensive overview of the challenges that ML techniques face in protecting cyberspace against attacks, by presenting a literature on ML techniques for cyber security including intrusion detection, spam detection, and malware detection on computer networks and mobile networks in the last decade. It also provides brief descriptions of each ML method, frequently used security datasets, essential ML tools, and evaluation metrics to evaluate a classification model. It finally discusses the challenges of using ML techniques in cyber security. This paper provides the latest extensive bibliography and the current trends of ML in cyber security.

show abstract

Applications in Security and Evasions in Machine Learning: A Survey

Cited by 52 publications

References 141 publications

Exploring Sybil and Double-Spending Risks in Blockchain Systems

Exploring Sybil and Double-Spending Risks in Blockchain Systems

Study on Inside Threats Based on Analytic Hierarchy Process

A Survey on Machine Learning Techniques for Cyber Security in the Last Decade

Contact Info

Product

Resources

About