Zero-Day Attack Identification in Streaming Data Using Semantics and Spark
Title | Zero-Day Attack Identification in Streaming Data Using Semantics and Spark |
Publication Type | Conference Paper |
Year of Publication | 2017 |
Authors | Pallaprolu, S. C., Sankineni, R., Thevar, M., Karabatis, G., Wang, J. |
Conference Name | 2017 IEEE International Congress on Big Data (BigData Congress) |
ISBN Number | 978-1-5386-1996-4 |
Keywords | anomaly detection, Cognition, collaborative classification methods, Collaborative mining, composability, Computer hacking, data streaming, defense, dynamic semantic graph generation, feature extraction, feature selection, Flow Creation, graph theory, groupware, IDS, Intrusion Detection Systems, learning (artificial intelligence), Metrics, minimum redundancy maximum relevance feature selection algorithm, MRMR feature selection algorithm, parallel detection, pattern classification, pubcrawl, Resiliency, security of data, semantic learning, Semantic learning and reasoning, semantic link networks, semantic reasoning, Semantics, SLN, Spark Streaming, Spark streaming platform, Sparks, Training, Zero day attacks, zero-day attack identification |
Abstract | Intrusion Detection Systems (IDS) have been in existence for many years now, but they fall short in efficiently detecting zero-day attacks. This paper presents an organic combination of Semantic Link Networks (SLN) and dynamic semantic graph generation for the on the fly discovery of zero-day attacks using the Spark Streaming platform for parallel detection. In addition, a minimum redundancy maximum relevance (MRMR) feature selection algorithm is deployed to determine the most discriminating features of the dataset. Compared to previous studies on zero-day attack identification, the described method yields better results due to the semantic learning and reasoning on top of the training data and due to the use of collaborative classification methods. We also verified the scalability of our method in a distributed environment. |
URL | http://ieeexplore.ieee.org/document/8029317/ |
DOI | 10.1109/BigDataCongress.2017.25 |
Citation Key | pallaprolu_zero-day_2017 |
- semantic reasoning
- MRMR feature selection algorithm
- parallel detection
- pattern classification
- pubcrawl
- Resiliency
- security of data
- semantic learning
- Semantic learning and reasoning
- semantic link networks
- minimum redundancy maximum relevance feature selection algorithm
- Semantics
- SLN
- Spark Streaming
- Spark streaming platform
- Sparks
- Training
- Zero day attacks
- zero-day attack identification
- feature extraction
- cognition
- collaborative classification methods
- Collaborative mining
- composability
- Computer hacking
- Data Streaming
- defense
- dynamic semantic graph generation
- Anomaly Detection
- Feature Selection
- Flow Creation
- graph theory
- groupware
- IDS
- Intrusion Detection Systems
- learning (artificial intelligence)
- Metrics