TY  - JOUR
T1  - Dynamic Correlation based Graded Intrusion Detection Architecture for Cloud
AU - Umamaheswari, K. AU - Sujatha, S. 
JO  - Asian Journal of Information Technology
VL  - 19
IS  - 9
SP  - 171
EP  - 180
PY  - 2020
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2020.171.180
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2020.171.180
KW  - Chakravyuha or padmavyuha
KW  -Intrusion Detection and Prevention Systems (IDPS)
KW  -multi-tier defense framework
KW  -SVM-SGD
KW  -system call analysis
KW  -VLAN
AB  - Data security and privacy are perennial
concerns related to cloud migration whether it is about
applications, business or customers. The multi-tenant
environment is vulnerable to several types of attacks that
hackers aiming towards the sensitive data in the broad
access area of cloud. Intrusion Detection and Protection
Systems (IDPS) are a significant part of the security
framework from the beginning of cloud usage. Since, the
security framework itself being the primary target of
attackers an unbreakable strategy is needed for its
protection. In this study, a novel security architecture for
cloud environment designed with IDPS components as a
graded multitier defense framework. The proposed model
is a defense formation of collaborative IDPS components
with dynamically revolving alert data placed in multiple
tiers of Virtual Local Area Networks (VLANs). Even if
many techniques existing for securing the cloud with
IDPS, the alert generation delays prevalent due to the
static correlation and aggregation. The novel security
architecture proposed with two contributions for
impregnable protection, one is to reduce alert generation
delay by dynamic correlation and the second is to support
the supervised learning of malware detection through,
system call analysis. The defense formation facilitates
malware detection with linear Support Vector
Machine-Stochastic Gradient Descent (SVM-SGD)
statistical algorithm. The proposed model of Dynamic
Correlated, Graded IDPS (DCGIDPS) for cloud requires
little computational effort to counter the distributed,
coordinated attacks efficiently.
ER  -