/Cyber_Security_Intrusion_Prevention

Creating a machine learning model to detect factors that contribute to cyber attacks in an effort to limit the vulnerability of the average consumer.

Primary LanguageJupyter Notebook

Cyber_Security_Intrusion_Prevention

Project Overview:

We are using a machine learning model to detect factors that contribute to DDoS cyber attacks in an effort to limit the vulnerability of the average consumer.

Defined Terms:

Benign: Harmless or well intentioned, the opposite of malicious.

DDoS: Distributed Denial of Service (DDoS). A term used to identify a type malicious attack.



Why did we chose this topic?

Living in a digital age, Cybersecurity is not only necessary but crucial. Preparedness is key to swiftly detecting and remedying an attack. Preventative measures can help secure your personal information and time from a legitimate cyber threat. We chose this topic to inform the general public of DDoS attacks, the common variables associated, and preventative measure they can take.


Link to Presentation Slides: Project Slides

Link to Tableau Dashboard: Tableau Dashboard

Questions we are seeking to answer with our data:

  1. How does a DDoS attack happen?

  2. What does a DDoS attack affect?

  3. Who is the target audience for DDoS attacks?

  4. What preventative measures can be taken to protect the average user from a malicious DDoS attack?

Description of our source data:

  • "The CICIDS2017 dataset consists of labeled network flows, including full packet payloads in pcap format, the corresponding profiles and the labeled flows (GeneratedLabelledFlows.zip) and CSV files for machine and deep learning purposes."

  • Intrusion Detection Evaluation Dataset (CIC-IDS2017) from the Canadian Institute for Cybersecurity.

    Description taken from: Data Source

Description of Data Exploration:

  • Explored numerical values of the cleaned DDoS dataframe.

  • Checked or outliers in the dataframe by creating and analyzing visualizations.

  • Explored each visualization for possible errors and anomalies.

  • Separated data to find the percentage of DDoS data and Benign data.

Description of Data Analysis phase:

  • Explore to find missing values and remove them.

  • Gather what columns would be useful to detect DDoS attacks.

  • Build a dataframe using the data attributed to DDoS attacks.

Cited_Resources:

  • Iman Sharafaldin, Arash Habibi Lashkari, and Ali A. Ghorbani, “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization”, 4th International Conference on Information Systems Security and Privacy (ICISSP), Portugal, January 2018

  • CISA. (2009, November 4). Understanding Denial-of-Service Attacks. National Cyber Awareness System. Retrieved November 1, 2022, from https://www.cisa.gov/uscert/ncas/tips/ST04-015

  • Link to Data Source

Software:

  • Tableau Public
  • VS Code
  • Pandas
  • Python
  • PostgresSQL

Data: