Network behavior anomaly detection (NBAD) is a security technique that provides network security threat detection. It is a complementary technology to systems that detect security threats based on packet signatures.[1]
NBAD is the continuous monitoring of a network for unusual events or trends. NBAD is an integral part of network behavior analysis (NBA), which offers security in addition to that provided by traditional anti-threat applications such as firewalls, intrusion detection systems, antivirus software and spyware-detection software.
Description
Most security monitoring systems utilize a signature-based approach to detect threats. They generally monitor packets on the network and look for patterns in the packets which match their database of signatures representing pre-identified known security threats. NBAD-based systems are particularly helpful in detecting security threat vectors in two instances where signature-based systems cannot: (i) new zero-day attacks, and (ii) when the threat traffic is encrypted such as the command and control channel for certain Botnets.
An NBAD program tracks critical network characteristics in real time and generates an alarm if a strange event or trend is detected that could indicate the presence of a threat. Large-scale examples of such characteristics include traffic volume, bandwidth use and protocol use.
NBAD solutions can also monitor the behavior of individual network subscribers. In order for NBAD to be optimally effective, a baseline of normal network or user behavior must be established over a period of time. Once certain parameters have been defined as normal, any departure from one or more of them is flagged as anomalous.
NBAD technology/techniques are applied in a number of network and security monitoring domains including: (i) Log analysis (ii) Packet inspection systems (iii) Flow monitoring systems and (iv) Route analytics.
NBAD has also been described as outlier detection, novelty detection, deviation detection and exception mining.[2]
