ABSTRACT
According to recent security trends, there are more variations of existing malware than new type malware. These malwares are causing a lot of damage, such as encrypting users ' data to leak personal information, delete data, and make financial demands. Although many studies are being conducted to analyze malwares in order to respond to the rapidly increasing malware with such malicious purpose, current malware analysis methods are for obfuscation, virtual environment bypass, etc. To overcome these difficulties, Deep Learning method that analyzes and utilizes harmful codes is receiving spotlight recently. Therefore, this thesis introduces trends on how to analyze malware based on Deep Learning.
- Kaspersky lab korea. report 26 % of the fastest evolving security threat, ransomware, is targeted at companies http://news.kaspersky.co.kr/news2017/12n/171201.htmGoogle Scholar
- Michael Sikorski, Andres Honig. 2012. Practical Malware analysis.Google Scholar
- Kyo-Il Chung, Han-na Park, Boo-Geum Jung, Jong-Soo Jang, Myung-Ae Chung. 2012. Big Data and Information Security. Korea Institute of Information Technology Magazine, 10(3), 17--22.Google Scholar
- Deep Learning from Scratch. 2016. O'Reilly JapanGoogle Scholar
- Daniel Gibert. Convolutional Neural Networks for Malware Classification. 2016. Master Thesis, Universitat de BarcelonaGoogle Scholar
- Jae Woon Park. 2016. Deep Learning Based Malware Detection Using API Features. Department of IT Convergence Information Security Graduate School of KonKuk Universi http://konkuk.dcollection.net/public_resource/pdf/000002316768_20180522134444.pdfGoogle Scholar
- Jun-ho Hwang, Tae-jin Lee. 2017. Android Malware Analysis Technology Research Based on Naive Bayes. Journal of the Korea Institute of Information Security & Cryptology, 27(5), 1087--1097.Google Scholar
- Hae Jung Kim, Eun Jun Yoon. 2017. Image-based Artificial Intelligence Deep Learning to Protect the Big Data from Malware. Journal of the Institute of Electronics and Information Engineers, 54(2), 76--82."Google Scholar
- Seonhee Seok, Howon Kim. 2016. Visualized Malware Classification Based-on Convolutional Neural Network. Journal of the Korea Institute of Information Security & Cryptology, 26(1), 197--208.Google ScholarCross Ref
- Sungtaek OH, Woong Go, Junhyung Park. 2017. A Study on the Machine Learning Algorithm for Mobile Malware Detection." Korea Information Science Society 1111--1113.Google Scholar
- Jin Hyun Yu. 2017. Study on DNN Based Android Malware Detection Method for Mobile Environment. Department of Information Security Graduate School of Information Security Korea UniversityGoogle Scholar
Index Terms
- Trend of Malware Detection Using Deep Learning
Recommendations
A Survey on Malware Detection with Deep Learning
SIN 2020: 13th International Conference on Security of Information and NetworksRapid development of Internet and technology has emerged a bunch of evolving malware and attack strategies. Therefore researchers focused on machine learning and deep learning methods to detect malware (viruses, bots, ransomware, trojans). In order to ...
Visualization and deep-learning-based malware variant detection using OpCode-level features
AbstractMalicious software (malware) is a major threat to the systems and networks’ security. Although anti-malware products are used to protect systems and networks against malware attacks, obfuscated malware that is capable of evading ...
Highlights- Detecting newly obfuscated malware remained a major challenge.
- Semisupervised ...
A comprehensive survey on deep learning based malware detection techniques
AbstractRecent theoretical and practical studies have revealed that malware is one of the most harmful threats to the digital world. Malware mitigation techniques have evolved over the years to ensure security. Earlier, several classical ...
Comments