Windows Based Data Sets for Evaluation of Robustness of Host Based Intrusion Detection Systems (IDS) to Zero-Day and Stealth Attacks

The Windows Operating System (OS) is the most popular desktop OS in the world, as it has the majority market share of both servers and personal computing necessities. However, as its default signature-based security measures are ineffectual for detecting zero-day and stealth attacks, it needs an intelligent Host-based Intrusion Detection System (HIDS). Unfortunately, a comprehensive data set that reflects the modern Windows OS’s normal and attack surfaces is not publicly available. To fill this gap, in this paper two open data sets generated by the cyber security department of the Australian Defence Force Academy (ADFA) are introduced, namely: Australian Defence Force Academy Windows Data Set (ADFA-WD); and Australian Defence Force Academy Windows Data Set with a Stealth Attacks Addendum (ADFA-WD: SAA). Statistical analysis results based on these data sets show that, due to the low foot prints of modern attacks and high similarity of normal and attacked data, both these data sets are complex, and highly intelligent Host based Anomaly Detection Systems (HADS) design will be required.

[1]  Xinghuo Yu,et al.  Evaluating Host-Based Anomaly Detection Systems: Application of the Frequency-Based Algorithms to ADFA-LD , 2014, NSS.

[2]  Jiankun Hu,et al.  Host-Based Anomaly Intrusion Detection , 2010, Handbook of Information and Communication Security.

[3]  Kim-Kwang Raymond Choo,et al.  Distributed denial of service (DDoS) resilience in cloud: Review and conceptual cloud DDoS mitigation framework , 2016, J. Netw. Comput. Appl..

[4]  Xinghuo Yu,et al.  Integer Data Zero-Watermark Assisted System Calls Abstraction and Normalization for Host Based Anomaly Detection Systems , 2015, 2015 IEEE 2nd International Conference on Cyber Security and Cloud Computing.

[5]  Laurence T. Yang,et al.  Data Exfiltration From Internet of Things Devices: iOS Devices as Case Studies , 2017, IEEE Internet of Things Journal.

[6]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.

[7]  Kim-Kwang Raymond Choo,et al.  A Review of Free Cloud-Based Anti-Malware Apps for Android , 2015, 2015 IEEE Trustcom/BigDataSE/ISPA.

[8]  Sheng-Hsun Hsu,et al.  Application of SVM and ANN for intrusion detection , 2005, Comput. Oper. Res..

[9]  Paul Byrne.  Defence-In-Depth: Application firewalls in a defence-in-depth design , 2006 .

[10]  Clifton L. Smith.  Understanding concepts in the defence in depth strategy , 2003, IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings..

[11]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Kim-Kwang Raymond Choo,et al.  Exfiltrating data from Android devices , 2015, Comput. Secur..

[13]  Jiankun Hu,et al.  A Semantic Approach to Host-Based Intrusion Detection Systems Using Contiguousand Discontiguous System Call Patterns , 2014, IEEE Transactions on Computers.

[14]  Gideon Creech,et al.  Developing a high-accuracy cross platform Host-Based Intrusion Detection System capable of reliably detecting zero-day attacks , 2014 .

[15]  Jiankun Hu,et al.  Towards reliable data feature retrieval and decision engine in host-based anomaly detection systems , 2015, 2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA).

[16]  Si Wu,et al.  Improving support vector machine classifiers by modifying kernel functions , 1999, Neural Networks.

[17]  Jiankun Hu,et al.  Generation of a new IDS test dataset: Time to retire the KDD collection , 2013, 2013 IEEE Wireless Communications and Networking Conference (WCNC).

[18]  Ali Dehghantanha,et al.  Ensemble-based multi-filter feature selection method for DDoS detection in cloud computing , 2016, EURASIP J. Wirel. Commun. Netw..