You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Issue Title: Develop LSTM Model for Malicious Node Detection in Proof-of-Stake Blockchain Dataset
Description:
We are using a dataset of over 10,000 entries that contains node data from a Proof-of-Stake (PoS) blockchain. The dataset was initially developed with 303 semi-synthetic entries and later augmented using Python to simulate more data. It includes both malicious and non-malicious nodes, making it ideal for detecting abnormal node behavior on a PoS blockchain.
Objective:
The task is to implement a Long Short-Term Memory (LSTM) model to detect malicious nodes in the dataset. The LSTM model will analyze node behavior over time and classify nodes as either malicious or non-malicious based on the sequential data provided.
Key Requirements:
LSTM Model: Design and train an LSTM model to classify nodes as malicious or non-malicious based on blockchain node data.
Data Preprocessing: Ensure the dataset is properly prepared for time series modeling, including normalization and reshaping of data for LSTM input.
Model Training: Train the LSTM model on the augmented dataset, splitting it into training and testing sets.
Evaluation: Use performance metrics such as accuracy, precision, recall, and F1-score to evaluate the model’s effectiveness in detecting malicious nodes.
Visualization: Provide visualizations for the training process (e.g., accuracy and loss curves) and classification performance (e.g., confusion matrix).
Tech Stack:
Python
TensorFlow/Keras (for LSTM implementation)
pandas and numpy (for data preprocessing)
matplotlib or seaborn (for visualization)
This is a crucial project for blockchain security research, especially for analyzing and improving the behavior of nodes in PoS blockchains. Please assign this issue to me for development under GSSOC Extd 2024.
The text was updated successfully, but these errors were encountered:
Thanks for creating the issue in ML-Nexus!🎉
Before you start working on your PR, please make sure to:
⭐ Star the repository if you haven't already.
Pull the latest changes to avoid any merge conflicts.
Attach before & after screenshots in your PR for clarity.
Include the issue number in your PR description for better tracking.
Don't forget to follow @UppuluriKalyani – Project Admin – for more updates!
Tag @Neilblaze,@SaiNivedh26 for assigning the issue to you.
Happy open-source contributing!☺️
Thanks for raising this issue! However, we believe a similar issue already exists. Kindly go through all the open issues and ask to be assigned to that issue.
Issue Title: Develop LSTM Model for Malicious Node Detection in Proof-of-Stake Blockchain Dataset
Description:
We are using a dataset of over 10,000 entries that contains node data from a Proof-of-Stake (PoS) blockchain. The dataset was initially developed with 303 semi-synthetic entries and later augmented using Python to simulate more data. It includes both malicious and non-malicious nodes, making it ideal for detecting abnormal node behavior on a PoS blockchain.
Objective:
The task is to implement a Long Short-Term Memory (LSTM) model to detect malicious nodes in the dataset. The LSTM model will analyze node behavior over time and classify nodes as either malicious or non-malicious based on the sequential data provided.
Key Requirements:
Tech Stack:
pandas
andnumpy
(for data preprocessing)matplotlib
orseaborn
(for visualization)This is a crucial project for blockchain security research, especially for analyzing and improving the behavior of nodes in PoS blockchains. Please assign this issue to me for development under GSSOC Extd 2024.
The text was updated successfully, but these errors were encountered: