INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
The back-end database is fundamental for storing enormous information created by Web trades, for example, cloud-facilitated applications and IoT shrewd gadgets. Interlopers keep on utilizing the Structured Query Language (SQL) Injection Attack (SQLIA) to take private data set data, and the outcomes will be appalling. The current methods, which are largely signature techniques, are unable to deal with new signatures hidden in internet requests because they were all developed prior to the most recent problems of massive data mining. To dissect and forestalling SQLIA, elective machine learning (ML) prescient examination gives a helpful and versatile technique for mining enormous amounts of information.
Unfortunately, a common issue in SQLIA research is the lack of strong corpora, or data sets, that contain patterns and historical data items and can be used to train classifiers. In this work, we explore the construction of a data set that incorporates extraction from known attack patterns. Some examples of these patterns include SQL words and symbols that are present at injection locations. The data set is pre-processed, labeled, and feature hashed for supervised learning. The trained classifier will intercept SQLIA in internet requests, stopping malicious internet requests to get to back-end database. This paper gives broad proof of the implementation of ML predictive analysis that predicts and keeps away from SQLIA by using observational evaluations expressed in the Confusion Matrix (CM) and Receiver Operating Curve (ROC).
Keywords:
SQLIA, SVM Classifier, Injection of SQL, data-driven SQLIA, Big data for SQLIA.
Cite Article:
"Prevention and Detection of SQL Injection Attack using Machine Learning Predictive Analytics", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 3, page no.c36-c42, March-2023, Available :http://www.ijnrd.org/papers/IJNRD2303207.pdf
Downloads:
000114578
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn