A Survey on Deep Learning Based Intrusion Detection System


UĞURLU M., DOĞRU İ. A.

2019 4th International Conference on Computer Science and Engineering (UBMK), Samsun, Turkey, Türkiye, 11 - 15 Eylül 2019 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/ubmk.2019.8907206
  • Basıldığı Şehir: Samsun, Turkey
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: Deep Learning, Intrusion Detection System, Cybersecurity
  • Gazi Üniversitesi Adresli: Evet

Özet

Although new technologies bring a lot of convenience to our lives, there are new problems in the field of cyber security. People use many critical applications such as e-commerce, e-banking, e-government and share critical data including personal data, account and credit card information. With the large amount of data produced and the increase in the zero-day attacks, the existing security applications are insufficient. In this context, deep learning algorithms have been used in cyber security applications. In the literature, deep learning application studies have been done in many areas like PC-based malware, android-based malware, intrusion detection system, phishing attack, cyber intelligence and spam detection. When the results of the studies were examined, it was observed that these studies' outputs give more successful results than the traditional security applications. A lot of studies have been done for many different network infrastructures such as traditional networks, IoT, SDN, Ad Hoc. In this paper, recent deep learning based intrusion detection systems are investigated.