|

|
IJE TRANSACTIONS B: Applications Vol. 30, No. 11 (November 2017) 1714-1722
|
Downloaded:
320 |
|
Viewed:
3245 |
|
|
NEURAL NETWORK BASED PROTECTION OF SOFTWARE DEFINED NETWORK CONTROLLER AGAINST DISTRIBUTED DENIAL OF SERVICE ATTACKS
|
|
|
F. Gharvirian and A. Bohlooli
|
|
|
( Received:
March 27, 2017
– Accepted in Revised Form: September 08, 2017 )
|
|
|
Abstract
Software
Defined Network (SDN)
is a new architecture for network management and its main concept is
centralizing network
management in the network control level
that has an overview of the network and determines the forwarding rules
for
switches and routers (the data level). Although this centralized control is the
main advantage of SDN, it is also a
single point of failure. If this main control
is made unreachable for any reason, the architecture of the network is
crashed.
A distributed denial of service (DDoS) attack is a threat for the SDN
controller which can make it unreachable.
In the previous researches in DDoS
detection in SDN, not enough work has been done on improvement of accuracy
in
detection. The proposed solution of this research can detect DDoS attack on SDN
controller with a noticeable accuracy
and prevents serious damage to the
controller. For this purpose, fast entropy of each flow is computed at certain
time
intervals. Then, by the use of adaptive threshold, the possibility of a
DDoS attack is investigated. In order to achieve
more accuracy, another method,
computing flow initiation rate, is used alongside. After observation of the
results of
this two methods, according to the described conditions, the
existence of an attack is confirmed or rejected, or this
decision is made at
the next step of the algorithm, with further study of flow statistics of
network switches by the
perceptron neural network. The evaluation results
show that the proposed algorithm has been able to make a
significant
improvement in detection rate and a reduction in false alarm rate
compared to closest previous work, besides maintaining
the average detection
time on an acceptable level.
|
|
|
Keywords
Software defined network, SDN, Neural Network, Distributed denial of service attack, DDoS, fast entropy
|
|
|
چکیده
شبکه نرمافزار محور یک معماری
جدید برای مدیریت شبکهها است که ایدهی اصلی آن متمرکزکردن منطق کنترل در سطح
کنترلکنندهی شبکه است که یک دید کلی از شبکه داشته و قوانین ارسال را به تمام
سوییچها و مسیریابهای شبکه(سطح داده) صادر میکند. این کنترلکنندهی مرکزی
اگرچه یک مزیت بزرگ است، اما اگر به هر دلیلی از دسترس خارج شود، شبکه سطح پردازش
خود را از دست داده و معماری آن از بین میرود. حملات محرومسازی از سرویس توزیعیافته
میتوانند کنترلکنندهی شبکه را از دسترس خارج نمایند. بیشتر کارهای انجام شده در
زمینهی تشخیص این حملات در شبکه نرمافزارمحور روی تشخیص زودهنگام تمرکز داشته و
کار کافی روی بهبود دقت در تشخیص انجام نگرفته است. راه
حل پیشنهادی این پژوهش میتواند حمله محرومسازی از سرویس توزيع شده به کنترلر
شبکهی نرم افزار را با دقت قابل توجهی تشخیص دهد و از وارد آمدن آسیب جدی به
کنترلر جلوگیری نماید. برای این منظور، آنتروپی سریع برای هر جریان در وقفههای
زمانی مشخص محاسبه میشود. سپس با استفاده از حد آستانهی تطبیقپذیر، احتمال یک
حمله محرومسازی از سرویس توزیعیافته بررسی میشود. برای دستیابی به دقت بیشتر در
کنار این روش، از یک روش دیگر، یعنی محاسبهی نرخ آغاز جریان هم استفاده میگردد.
پس از مشاهدهی نتایج این دو روش، بر اساس شرایطی که در متن توضیح داده خواهد شد،
وجود یک حمله تایید یا رد میشود و یا اینکه این تصمیم در مرحلهی بعدی با بررسی
آمارهای جریان سوییچهای شبکه توسط شبکه عصبی پرسپترون، انجام میگیرد.نتایج
ارزیابی نشان میدهد که الگوریتم پیشنهادی قادر است یک بهبود مهم در نرخ تشخیص و
یک کاهش در نرخ اعلام خطا، نسبت به مرتبطترین کار قبلی ایجاد نماید و علاوهبراین
میانگین زمان تشخیص الگوریتم را نیز در یک سطح قابل قبول نگه دارد.
|
|
References
1. Ali, S.T., Sivaraman, V.,
Radford, A. and Jha, S., "A survey of securing networks using software
defined networking", IEEE Transactions on Reliability, Vol. 64, No. 3, (2015), 1086-1097.
2. Vizváry,
M. and Vykopal, J., "Future of ddos attacks mitigation in software defined
networks", in IFIP International Conference on Autonomous Infrastructure,
Management and Security, Springer., (2014), 123-127.
3. Wang,
H.-z., Zhang, P., Xiong, L., Liu, X. and Hu, C.-c., "A secure and
high-performance multi-controller architecture for software-defined
networking", Frontiers of Information Technology & Electronic Engineering, Vol. 17, No. 7, (2016), 634-646.
4. Oktian,
Y.E., Lee, S. and Lee, H., "Mitigating denial of service (dos) attacks in
openflow networks", in Information and Communication Technology
Convergence (ICTC), 2014 International Conference on, IEEE., (2014), 325-330.
5. Jeyanthi,
N., Shabeeb, H., Durai, M.S. and Thandeeswaran, R., "Rescue: Reputation
based service for cloud user environment", International Journal of
Engineering-Transactions B: Applications, Vol. 27, No. 8, (2014), 1179-1185.
6. Yan,
Q. and Yu, F.R., "Distributed denial of service attacks in
software-defined networking with cloud computing", IEEE Communications Magazine, Vol. 53, No. 4, (2015), 52-59.
7. Braga,
R., Mota, E. and Passito, A., "Lightweight ddos flooding attack detection
using nox/openflow", in Local Computer Networks (LCN), 2010 IEEE 35th
Conference on, IEEE., (2010), 408-415.
8. Bohlooli,
A. and Jamshidi, K., "A gps-free method for vehicle future movement
directions prediction using som for vanet", Applied Intelligence, Vol. 36, No. 3, (2012), 685-697.
9. No,
G. and Ra, I., "Adaptive ddos detector design using fast entropy
computation method", in Innovative Mobile and Internet Services in
Ubiquitous Computing (IMIS), 2011 Fifth International Conference on, IEEE.,
(2011), 86-93.
10. David, J. and Thomas, C., "Ddos attack
detection using fast entropy approach on flow-based network traffic", Procedia
Computer Science, Vol. 50, (2015),
30-36.
11. Lim, S., Yang, S., Kim, Y., Yang, S. and
Kim, H., "Controller scheduling for continued sdn operation under ddos
attacks", Electronics Letters,
Vol. 51, No. 16, (2015), 1259-1261.
12. Mousavi, S.M. and St-Hilaire, M.,
"Early detection of ddos attacks against sdn controllers", in
Computing, Networking and Communications (ICNC), International Conference on,
IEEE., (2015), 77-81.
13. G., V., N., S.S. and Manikandan MSK.,
"Navie bayes intrusion
classification system for voice
over internet protocol network using
honeypot", International Journal of Engineering Transaction A: Basics, Vol. 28, No. 1, (2015), 44-51.
14. Kia, M., "Early detection and
mitigation of ddos attackin software defined networks", Ryerson
University, Toronto, Ontario, Canada, Ms.c.
(2015),
15. Khozani, Z.S., Bonakdari, H. and Zaji, A.,
"Comparison of three soft computing methods in estimating apparent shear
stress in compound channels" International Journal of Engineering Transaction C: Aspects,
Vol. 29, No. 9, (2016) , 1219-1226..
16. Pradeep, J., Srinivasan, E. and Himavathi,
S., "Neural network based recognition system integrating feature
extraction and classification for english handwritten", International
Journal of Engineering-Transactions B: Applications, Vol. 25, No. 2, (2012), 99-107.
17. Shamaei, E. and Kaedi, M., "Suspended
sediment concentration estimation by stacking the genetic programming and
neuro-fuzzy predictions", Applied Soft Computing, Vol. 45, (2016), 187-196.
18. Prete, L.R., Schweitzer, C.M., Shinoda, A.A.
and de Oliveira, R.L.S., "Simulation in an sdn network scenario using the
pox controller", in Communications and Computing (COLCOM), IEEE Colombian
Conference on, IEEE., (2014), 1-6.
19. Bohlooli A., Jamshidi K., "Profile based routing
in vehicular ad-hoc networks", Science China Information Sciences,
Vol. 57, No. 6, (2014). 1-11.
|
|
|
|
|