Obini, U. C.
Critical review of file-less malware, attacks and detection techniques for mitigating them - Vol.25(4), Jul-Aug - Haryana IOSR - International Organization of Scientific Research 2023 - 34-41p.
This paper presented a critical study of file-less malware attacks and the detection techniques for mitigating
these attacks on computer systems or software platforms. The study started by presenting an overview of file-
less malwares, types of the file-less malwares that can be encountered and various techniques adopted in
detecting and tackling the challenges posed by file-less malwares. The work studied signature-based technique,
behavior-based technique, heuristic methods, IoT-based methods and machine learning methods. Further in the
work, we introduced adversarial machine learning technique and how attackers implement this technique for
the development of intelligent malware that is capable of maneuvering other detection techniques. In this work,
the application of machine learning (deep neural network) has been presented as the most effective means that
can be applied for an effective detection of file-less malware of any type. Consequently, the study recommended
that future research works should aim at adopting deep learning techniques for the mitigation of adversarial
and in fact all types of file-less malware attacks.
Computer Engineering
Critical review of file-less malware, attacks and detection techniques for mitigating them - Vol.25(4), Jul-Aug - Haryana IOSR - International Organization of Scientific Research 2023 - 34-41p.
This paper presented a critical study of file-less malware attacks and the detection techniques for mitigating
these attacks on computer systems or software platforms. The study started by presenting an overview of file-
less malwares, types of the file-less malwares that can be encountered and various techniques adopted in
detecting and tackling the challenges posed by file-less malwares. The work studied signature-based technique,
behavior-based technique, heuristic methods, IoT-based methods and machine learning methods. Further in the
work, we introduced adversarial machine learning technique and how attackers implement this technique for
the development of intelligent malware that is capable of maneuvering other detection techniques. In this work,
the application of machine learning (deep neural network) has been presented as the most effective means that
can be applied for an effective detection of file-less malware of any type. Consequently, the study recommended
that future research works should aim at adopting deep learning techniques for the mitigation of adversarial
and in fact all types of file-less malware attacks.
Computer Engineering