Using Dtrace for Machine Learning Solutions in Malware Detection

P, Aiswarya Mohan K; Chandran, Saranya; Gressel, Gilad; U, None Arjun T; Pavithran, Vipin

doi:10.1109/icccnt49239.2020.9225633

Cited by 4 publications

(7 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Range of Detection Accuracy Rate K-Means [53], [54] 88% -> 90% NB [29], [38], [39], [40], [41], [54], [57], Pang, [58], [59], [60], [61], [74], [84], [91], [97], [101] 73.01% -98% SVM [36], [39], [40], [41], [45], [46], [47], [48], [51], [55], [61], [64], [65], [75], [78], [79], [80], [81], [82], [83], [84], [85], [86], [94], [95], [99], [100], [101] 64.7% -100% DT [29], [33], [34], [35]<...…”

Section: Related Workmentioning

confidence: 99%

“…This method is essentially a manual comparison of some systems' typical actions. Lowering the , [55], [58], [59], [62], [63], [65], [68], [72], [73], [74], [75], [78], [79], [80], [82], [86], [91], [92], [93], [95], [97], [103], [104], [106], [107], [108], [110], [111], [112], [114], [115], [116], [117], [118], [120], [122], [123], [126] Behaviorbased…”

Section: D: Specification-basedmentioning

confidence: 99%

“…Dataset issues were found as the most common research gap in the selected studies. It is not only because the size of the dataset is small [59], [63], [72]; the lack of a standard dataset benchmark [58] also contributed to this issue. Besides, various types of datasets were used in the experiment leading to poor performance [61], [69].…”

Section: A Dataset Usedmentioning

confidence: 99%

“…Furthermore, the outdated dataset used in the experiment, which offers little or no utility as a benchmark for the performance of malware detection systems on a modern network [119], also contributed to this issue. [53], [58], [59], [65], [68], [78], [79], [82], [86], [91], [95], [97], [103], [104], [106], [108], [111], [112], [115], [118], [120], [122], [123] Dynamic 2 6 5 9 2 2 1 1 2 0 2 [55], [62], [63], [72], [74], [75], [92], [93], [107], [110], [113], [114], [116], [117], [126] Hybrid 2 4 3 4 1 0 0 3 1 1 3 [54], [56], [57], [60], [61], [64], [66], [67], [69], [70]...…”

Section: A Dataset Usedmentioning

confidence: 99%

“…It is essential to test the robustness of the clustering mechanisms against adversarial samples [58] and their usability in the cloud environment by evaluating the model performance on a larger dataset. Since most of the issues related to the dataset are about the insufficient dataset, a more extensive dataset [59] is needed during empirical experiments for more accurate training of the model and to expand the known malware [99]. Furthermore, evaluation using a more extensive range of malware is essential [102] so that the results can be more representative.…”

Section: Datasetmentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning Algorithm for Malware Detection: Taxonomy, Current Challenges, and Future Directions

et al. 2023

View full text Add to dashboard Cite

Malware has emerged as a cyber security threat that continuously changes to target computer systems, smart devices, and extensive networks with the development of information technologies. As a result, malware detection has always been a major worry and a difficult issue, owing to shortcomings in performance accuracy, analysis type, and malware detection approaches that fail to identify unexpected malware attacks. This paper seeks to conduct a thorough literature review and offer a taxonomy of machine learning methods for malware detection that considers these problems by analyzing 77 chosen research works. The research investigates malware and machine learning in the context of cybersecurity, including malware detection taxonomy and machine learning algorithm classification into numerous categories. Furthermore, the taxonomy was used to evaluate the most recent machine learning algorithm and analysis. The paper also examines the obstacles and associated concerns encountered in malware detection and potential remedies. Finally, to address the related issues that would motivate researchers in their future work, an empirical study was utilized to assess the performance of several machine learning algorithms.INDEX TERMS Malware detection, machine learning algorithms, state-of-the-art.

show abstract