A Statistical Anomaly Detection Technique based on Three Different Network Features Yuji Waizumi Tohoku Univ.

Slides:



Advertisements
Similar presentations
Applications of one-class classification
Advertisements

Network Monitoring System In CSTNET Long Chun China Science & Technology Network.
Wenke Lee and Nick Feamster Georgia Tech Botnet and Spam Detection in High-Speed Networks.
REFLEX INTRUSION PREVENTION SYSTEM.. OVERVIEW The Reflex Interceptor appliance is an enterprise- level Network Intrusion Prevention System. It is designed.
An Introduction of Botnet Detection – Part 2 Guofei Gu, Wenke Lee (Georiga Tech)
CISCO NETWORKING ACADEMY PROGRAM (CNAP)
Decision Trees for Server Flow Authentication James P. Early and Carla E. Brodley Purdue University West Lafayette, IN 47907
Polymorphic blending attacks Prahlad Fogla et al USENIX 2006 Presented By Himanshu Pagey.
INDEX  Ethical Hacking Terminology.  What is Ethical hacking?  Who are Ethical hacker?  How many types of hackers?  White Hats (Ethical hackers)
Network Intrusion Detection Systems Presented by Keith Elliott.
 Firewalls and Application Level Gateways (ALGs)  Usually configured to protect from at least two types of attack ▪ Control sites which local users.
5/1/2006Sireesha/IDS1 Intrusion Detection Systems (A preliminary study) Sireesha Dasaraju CS526 - Advanced Internet Systems UCCS.
Unsupervised Intrusion Detection Using Clustering Approach Muhammet Kabukçu Sefa Kılıç Ferhat Kutlu Teoman Toraman 1/29.
Statistical based IDS background introduction. Statistical IDS background Why do we do this project Attack introduction IDS architecture Data description.
IDS/IPS Definition and Classification
Mining Behavior Models Wenke Lee College of Computing Georgia Institute of Technology.
FIREWALLS & NETWORK SECURITY with Intrusion Detection and VPNs, 2 nd ed. 6 Packet Filtering By Whitman, Mattord, & Austin© 2008 Course Technology.
Testing Intrusion Detection Systems: A Critic for the 1998 and 1999 DARPA Intrusion Detection System Evaluations as Performed by Lincoln Laboratory By.
Lecture 11 Intrusion Detection (cont)
Using Argus Audit Trails to Enhance IDS Analysis Jed Haile Nitro Data Systems
Intrusion Detection System Marmagna Desai [ 520 Presentation]
INTRUSION DETECTION SYSTEMS Tristan Walters Rayce West.
Guofei Gu, Roberto Perdisci, Junjie Zhang, and Wenke Lee College of Computing, Georgia Institute of Technology USENIX Security '08 Presented by Lei Wu.
Lucent Technologies – Proprietary Use pursuant to company instruction Learning Sequential Models for Detecting Anomalous Protocol Usage (work in progress)
1 Intrusion Detection Systems. 2 Intrusion Detection Intrusion is any use or attempted use of a system that exceeds authentication limits Intrusions are.
Information Systems CS-507 Lecture 40. Availability of tools and techniques on the Internet or as commercially available software that an intruder can.
Packet Filtering. 2 Objectives Describe packets and packet filtering Explain the approaches to packet filtering Recommend specific filtering rules.
Intrusion Detection for Grid and Cloud Computing Author Kleber Vieira, Alexandre Schulter, Carlos Becker Westphall, and Carla Merkle Westphall Federal.
Network Flow-Based Anomaly Detection of DDoS Attacks Vassilis Chatzigiannakis National Technical University of Athens, Greece TNC.
Network Intrusion Detection Using Random Forests Jiong Zhang Mohammad Zulkernine School of Computing Queen's University Kingston, Ontario, Canada.
IDS Intrusion Detection Systems CERT definition: A combination of hardware and software that monitors and collects system and network information and analyzes.
Intrusion Prevention System. Module Objectives By the end of this module, participants will be able to: Use the FortiGate Intrusion Prevention System.
INTRUSION DETECTION INTRUSION DETECTION INTRUSION DETECTION INTRUSION DETECTION INTRUSION DETECTION INTRUSION DETECTION INTRUSION DETECTION INTRUSION DETECTION.
ECE4112 Lab 7: Honeypots and Network Monitoring and Forensics Group 13 + Group 14 Allen Brewer Jiayue (Simon) Chen Daniel Chu Chinmay Patel.
Honeypot and Intrusion Detection System
11 Automatic Discovery of Botnet Communities on Large-Scale Communication Networks Wei Lu, Mahbod Tavallaee and Ali A. Ghorbani - in ACM Symposium on InformAtion,
Intrusion Detection and Prevention. Objectives ● Purpose of IDS's ● Function of IDS's in a secure network design ● Install and use an IDS ● Customize.
An Analysis of the 1999 DARPA/Lincoln Laboratory Evaluation Data for Network Anomaly Detection Matthew V. Mahoney and Philip K. Chan.
Source-End Defense System against DDoS attacks Fu-Yuan Lee, Shiuhpyng Shieh, Jui-Ting Shieh and Sheng Hsuan Wang Distributed System and Network Security.
--Harish Reddy Vemula Distributed Denial of Service.
DoWitcher: Effective Worm Detection and Containment in the Internet Core S. Ranjan et. al in INFOCOM 2007 Presented by: Sailesh Kumar.
Detection Unknown Worms Using Randomness Check Computer and Communication Security Lab. Dept. of Computer Science and Engineering KOREA University Hyundo.
Packet Filtering Chapter 4. Learning Objectives Understand packets and packet filtering Understand approaches to packet filtering Set specific filtering.
Fuzzy Network Profiling for Intrusion Detection Dickerson, J.E.; Dickerson, J.A. Fuzzy Information Processing Society, NAFIPS. 19th International.
Copyright © 2003 OPNET Technologies, Inc. Confidential, not for distribution to third parties. Session 1341: Case Studies of Security Studies of Intrusion.
IEEE Communications Surveys & Tutorials 1st Quarter 2008.
Firewalls  Firewall sits between the corporate network and the Internet Prevents unauthorized access from the InternetPrevents unauthorized access from.
SNORT Biopsy: A Forensic Analysis on Intrusion Detection System By Asif Syed Chowdhury.
Open-Eye Georgios Androulidakis National Technical University of Athens.
Alexey A. Didyk Kherson national technical university, Ukraine
Mining Anomalies Using Traffic Feature Distributions Anukool Lakhina Mark Crovella Christophe Diot in ACM SIGCOMM 2005 Presented by: Sailesh Kumar.
Cryptography and Network Security Sixth Edition by William Stallings.
Intrusion Detection Systems Paper written detailing importance of audit data in detecting misuse + user behavior 1984-SRI int’l develop method of.
1 Virtual Dark IP for Internet Threat Detection Akihiro Shimoda & Shigeki Goto Waseda University
Machine Learning for Network Anomaly Detection Matt Mahoney.
Role Of Network IDS in Network Perimeter Defense.
1 CURELAN TECHNOLOGY Co., LTD Flowviewer FM-800A CURELAN TECHNOLOGY Co., LTD
Firewalls. Overview of Firewalls As the name implies, a firewall acts to provide secured access between two networks A firewall may be implemented as.
Some Great Open Source Intrusion Detection Systems (IDSs)
Snort – IDS / IPS.
NET 412 Network Security protocols
DDoS Attack Detection under SDN Context
A survey of network anomaly detection techniques
Lecture 8: Intrusion Detection
Intrusion Detection system
Transport Layer Identification of P2P Traffic
Statistical based IDS background introduction
Intrusion Detection Systems
Lecture 7: Intrusion Detection
When Machine Learning Meets Security – Secure ML or Use ML to Secure sth.? ECE 693.
Presentation transcript:

A Statistical Anomaly Detection Technique based on Three Different Network Features Yuji Waizumi Tohoku Univ.

Background The Internet has entered the business world Need to protect information and systems from hackers and attacks Network security has been becoming important issue Many intrusion/attack detection methods has been proposed

Intrusion Detection System Two major detection principles: Signature Detection  Attempts to flag behavior that is close to some previously defined pattern signature of a known intrusion Anomaly Detection  Attempts to quantify the usual or acceptable behavior and flags other irregular behavior as potentially intrusive.

Motivation Anomaly detection system Pro: can detect unknown attacks Con: many false positives Improve the performance of Anomaly detection system Analyze the characteristics of attacks Propose method to construct features as numerical values from network traffic Construct detection system using the features

Classification of Attacks DARPA Intrusion Detection Evaluation DoS: Denial of Service Probe: Surveillance of Targets Remote to Local(R2L), User to Root(U2R): Unauthorized Access to a Host or Super User

Re-classification of Attacks Classification by Traffic Characteristics DoS, Probe  Traffic Quantity  Access Range Probe  Structure of Communication Flows DoS, R2L, U2R  Contents of Communications To detect attacks with above characteristics, it is necessary to construct features corresponding those classes.

Network Traffic Feature Numerical values(vectors) expressing state of traffic We propose three different network feature sets Based of re-classification of attacks Analyzed independently

Time Slot Feature (34 dimension) Count various packets, flags, transmission and reception bytes, and port variety by a unit time Estimate scale and range of attacks Target Probe (Scan) DoS Each slot is expressed as a vector Ex) (TCP,icmp,SYN,FIN,RST,UDP,DNS, … )

Examples (Time Slot Feature) normal traffic only rst flag (port 21) rst flag (port 23) ftp scantelnet scan Vector element Element value Values are regularizes as mean=0, variance=1.0

Flow Counting Feature Flow is specified by (srcIP, dstIP, srcPort,dstPort,protocol) Count packets, flags, transmission and reception bytes in a flow Target Scan with illegal flags Ports used as backdoors TCP:19 dim., UDP:7 dim.

Examples (Flow Counting Feature) Normal traffic Port sweep(scan) Decrease of SYN packet Vector element Element value Specific packets of attacks are extremely high and low.

Flow Payload Feature Represent content of communication Histogram of character codes of a flow Count 8bit-unit(256 class) Transmission and reception are counted independently (total 512 class) Target Buffer overflow Malicious code

Examples (Flow Payload Feature) Specific character of attacks are extremely high and low. Normal traffic imap attack

Modeling Normal Behavior Each packet appears based on protocol Correlations between elements of the feature vectors Profile based on correlations can represent normal behavior of network traffic

Principal Component Analysis:PCA Extract correlation among samples as Principal Component Principal Component lay along sample distribution Principal Component Non-correlated data

Discriminant Function Projection Distance Principal Component Anomaly sample Projection Distance Long Distant Samples: Unordinary traffic Break Correlation Detection Criterion

Detection Algorithm Independent Detection The three features are used for PCA independently "Logical OR" operation for detection alerts by each feature Time Slot Flow Counting Flow Payload Features Network Traffic PCA Alert OR Alert

Performance Evaluation Two Examine Scenario Scenario1  Learn Week1 and 3  Test Week4 and 5 Scenario2  Learn Week 4 and 5  Test Week 4 and 5  More Practical Situation Real network traffic may include attack traffic Criterion for Evaluation Detection rate when number of miss-detection (false positive) per day is 10

Data Set 1999 DARPA off-line intrusion detection evaluation test set Contain 5 weeks data (from Monday to Friday) Week1,3: Normal traffic only Week2: Including attacks (for learning) Week4,5: Including attacks (for testing)

Scenario 1 Result # of detection # of target Detection rate Proposed Method % NETAD % Forensics % Expert % Expert % Dmine %

Scenario 2 Result # of detection # of target Detection rate Proposed Method % NETAD % NETAD Use IP address as white list Overfit learning data Proposed Method Independent of IP address Evaluate only anomaly of traffic

Detection Results every Features ( FP )( FC ) ( TS ) 3 ( TS ) & ( FC ) & ( FP ) 40 Flow Payload(FP ) 38 Flow Counting ( FC ) 2737 Time Slot Feature ( TS ) ( FP ) ( FC )( TS ) 5 ( TS ) & ( FC ) & ( FP ) 44 Flow Payload Feature(FP) 613 Flow Counting Feature(FC) 5922Time Slot Feature(TS) Scenario 1 Scenario 2 # of Detection by both TS & FP # of Detection by FP only # of Detection by all Three Features Low detection overlap Each feature detect different characteristic attacks

Conclusion For network security Classification attacks into three types Construct three features corresponding to three attack characteristics Detection method with PCA  Learning the three features independently Higher detection accuracy  With samples including attacks