شبکه عصبی عمیق ترکیبی بهینه ادغام شده با انتخاب ویژگی برای سامانه تشخیص نفوذ در حملات سایبری

ﻫﻤﺮاه ﺑﺎ ﭘﯿﺸﺮﻓﺖ ﺳﺮﯾﻊ روش ﻫﺎی ﯾﺎدﮔﯿﺮی ﻣﺎﺷﯿﻦ ml و ﯾﺎدﮔﯿﺮی ﻋﻤﯿﻖ dl در دﻧﯿﺎی داده، ﯾﮑﯽ از ﮐﺎرﺑﺮدﻫ ﺎی ﻣﻬﻢ آن ﻫ ﺎ در ﺣﻤﻼت ﺳﺎﯾﺒﺮی، ﺑﻪ ﺳﯿﺴﺘﻢ ﻫﺎی ﺗﺸﺨﯿﺺ ﻧﻔﻮذ ids ﺑﺎ اﺳﺘﻔﺎده از اﻟﮕﻮرﯾﺘﻢ ﻫﺎی ﻃﺒﻘﻪ ﺑﻨﺪی ﭘﯿﺸﺮﻓﺘﻪ اﺧﺘﺼﺎص ﻣﯽ ﯾﺎﺑﺪ . ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ اﻫﻤ ﯿﺖ ﺣﻔﻆ اﻃﻼﻋﺎت اﯾﻤﻦ و ﺣﯿﺎﺗﯽ ﺳﺎزﻣﺎن ﻫﺎ ﯾﺎ اﻓﺮاد در ﺑﺮاﺑﺮ ﺣﻤﻼت ﻧﻔﻮذﮔﺮان، ids ﻣﻮﺿﻮع ﺗﺤﻘﯿﻘﺎت ﻣﺘﻌﺪدی ﺟﻬﺖ اﻓﺰاﯾﺶ دﻗﺖ و ﻗﺎﺑﻠ ﯿﺖ اﻃﻤﯿﻨﺎن ﺑﻮده اﺳﺖ. در ﻧﺘﯿﺠﻪ، اﯾﻦ ﻣﻘﺎﻟﻪ ﯾﮏ ﻣﺪل ﺗﺮﮐﯿﺒﯽ را اراﺋﻪ ﻣﯽ ﮐﻨﺪ ﮐﻪ ﺑﻪ ادﻏﺎم اﻧﺘﺨﺎب وﯾﮋﮔﯽ، ﻃﺒﻘﻪ ﺑﻨﺪی و ﺑﻬﯿﻨﻪ ﺳﺎزی ﻫﺎﯾﭙﺮﭘﺎراﻣﺘﺮﻫﺎ ﭘﺮداﺧﺘﻪ اﺳﺖ. اﺑﺘﺪا، وﯾﮋﮔﯽ ﻫﺎی ﮐﺎﻧﺪﯾﺪ اوﻟﯿﻪ ﺑﻪ ﻃﻮر ﻫﻢ زﻣﺎن و ﺟﺪاﮔﺎﻧﻪ ﺗﻮﺳﻂ روش ﻫﺎی اﻃﻼﻋﺎت ﻣﺘﻘﺎﺑﻞ اﺻﻼح ﺷﺪه mmi ، اﻟﮕﻮرﯾﺘﻢ ژﻧﺘﯿﮏ ga و آزﻣﻮن f ﺗﺤﻠﯿﻞ وارﯾﺎﻧﺲ اﻧﺘﺨﺎب ﻣﯽ ﺷﻮﻧﺪ و ﭘﺲ ازآن، رای ﮔﯿﺮی ﺟﻬﺖ اﺳﺘﺨﺮاج ﻫﻤﻪ وﯾﮋﮔﯽ ﻫﺎی ﻣﺸﺘﺮک ﺑﻪ ﻋﻨﻮان ﻣﺘﻐ ﯿﺮﻫﺎی ورودی ﺻﻮرت ﻣﯽ ﭘﺬﯾﺮد. در اداﻣﻪ، ﯾﮏ ﻃﺒﻘﻪ ﺑﻨﺪ ﺗﺮﮐﯿﺒﯽ cnn و cnn lstm lstm ﺑﻪ ﮐﺎر ﮔﺮﻓﺘﻪ ﻣﯽ ﺷﻮد ﮐﻪ ﻫﺎﯾﭙﺮﭘﺎراﻣﺘﺮﻫﺎی آن ﺗﻮﺳﻂ ﯾﮏ اﻟﮕﻮر ﯾﺘﻢ ﺑﻬﯿﻨﻪ ﺳﺎزی ﮔﺮگ ﺧﺎﮐﺴﺘﺮی ﻧﻬﻨﮓ ﺑﺎ ﺟﺎﺑﺠﺎﯾﯽ ﺗﺼﺎدﻓﯽ rs gwo woa ﺗﻌﯿﯿﻦ ﺧﻮاﻫﺪ ﺷﺪ. ﺑﻪ ﻣﻨﻈﻮر ﺗﺠﺰ ﯾﻪ وﺗﺤﻠﯿﻞ ﻃﺮح ﭘﯿﺸﻨﻬﺎدی، ﻣﻘﺎﯾﺴﻪ ای ﺑﺎ ﺳﺎﯾﺮ روشﻫﺎ از ﻧﻈﺮ ﺻﺤﺖ، دﻗﺖ، ﯾﺎدآوری، اﻣﺘﯿﺎز f1 و زﻣﺎن در ﻣﺠﻤﻮﻋﻪ داده nsl kdd اﻧﺠﺎم ﺷﺪه اﺳﺖ ﮐﻪ ﺑﺮﺗﺮ ی روﯾﮑﺮد ﺗﻮﺳﻌﻪ ﯾﺎﻓﺘﻪ را ﺗﺎﺋﯿﺪ ﻣﯽ ﻧﻤﺎﯾﺪ.

an optimized compound deep neural network integrating with feature selection for intrusion detection system in cyber attacks

in today’s digital era, security issues and cyber attacks have become a serious and attention needed concern as they hamper secured and vital information relating to organizations or individuals. accordingly, timely detection of these vulnerabilities made by intruders is essential, wherein the cornerstone of security ensures the user’s data privacy as an intrusion detection system ids . on the other hand, with the rapid development of machine learning ml and deep learning dl methods in the data world, one of their significant applications is dedicated to ids using state of the art classification algorithms, which has been the subject of numerous research to enhance accuracy and reliability in recent years. as a consequence, this paper presents a hybrid model integrating feature selection, classification, and hyper parameters optimization. first, the initial massive features are subjected separately to the modified mutual information mmi , genetic algorithm ga , and anova f value approaches, followed by extracting the common outputs as optimal and reduced final features. subsequently, a compound cnn and lstm classifier cnn lstm is employed, where its hyper parameters will be determined through a random switch grey wolf whale optimization algorithm rs gwo woa instead of a time consuming trial and error manual process. ultimately, to analyze the suggested scheme, a comparison with other strategies in terms of accuracy, precision, recall, f1 score, and periods of time on the nsl kdd dataset has been accomplished, confirming the superiority of the developed approach.