Inspiration

We have already submitted this project in a Hackathon yesterday 11th September 2022 for Codezen Introductory Webathon and awaiting the results

We always wanted to try Cyber Security related Projects. So we saw Intrusion Detection System as a way to implement it. We were astounded by the fact that: it detects and responds to malicious traffic. The primary benefit of an intrusion detection system is to ensure IT personnel is notified when an attack or network intrusion might be taking place. Also employs technology, that analyses traffic flows to the protected resource in order to detect and monitors all incoming and outgoing network activity and identifies any signs of intrusion in your system

What it does

Our Intrusion Detection System is a software application which is employed to detect network intrusion using machine learning {Random Forest} algorithms. A predictive model (i.e. a classifier) was built which was capable of distinguishing between ‘bad connections’ (intrusion/attacks) and ‘good (normal) connections’.

How we built it

  1. We used React js along with Tailwind CSS in the front end. Flask was integrated to connect Machine Learning to connect with the front end.
  2. It detects the attacks on the basis of specific patterns such as number of bytes or number of 1's or number of 0's in the network traffic. It also detects on the basis of the already known malicious instruction sequence that is used by the malware. ## Challenges we ran into This was our first time training a Machine Learning Model. We were inexperienced in handling the datasets. We had to learn about various Intrusions : -DOS: denial-of-service, e.g. syn flood; -R2L: unauthorized access from a remote machine, e.g. guessing password; -U2R: unauthorized access to local superuser (root) privileges, e.g., various “buffer overflow” attacks; -probing: surveillance and another probing, e.g., port scanning. ##Datasets Used {Infos fetched from GeeksforGeeks} Dataset Used : KDD Cup 1999 dataset -Dataset Description: Data files: -kddcup.names : A list of features. -kddcup.data.gz : The full data set -kddcup.data_10_percent.gz : A 10% subset. -kddcup.newtestdata_10_percent_unlabeled.gz -kddcup.testdata.unlabeled.gz -kddcup.testdata.unlabeled_10_percent.gz -corrected.gz : Test data with corrected labels. -training_attack_types : A list of intrusion types. -typo-correction.txt : A brief note on a typo in the data set that has been corrected ## Cyber Desk Novelty and Features
  3. Cross Platform-both web and Mobile
  4. Functional React Hooks
  5. A Custom Trained ML Model
  6. Accurate Intrusion Detection
  7. Specifying both Intrusion and its types

What's next for Cyber Desk

-Since Malware on Twitter is on the rise. Accounts may become compromised if you've entrusted your username and password to a malicious third-party application or website. So our next attempt will be in Scrapping them using SQUINT {Python}. -Identifying Intrusions through Images, pdf, etc.

Built With

Share this project:

Updates