cyber-security-resources/ai_research
2023-10-23 22:24:25 -04:00
..
AI for Incident Response organizing resources 2023-09-04 23:49:06 -04:00
AI Security Best Practices Update threat-modeling.md 2023-10-23 22:12:05 -04:00
ethics_privacy Update README.md 2023-09-08 11:54:12 -04:00
labs Update tf_keras.md 2023-09-05 21:42:32 -04:00
LangChain Update README.md 2023-10-23 22:24:25 -04:00
LLM-frameworks Create README.md 2023-10-23 22:21:19 -04:00
ML_Fundamentals Update README.md 2023-09-05 00:39:03 -04:00
prompt_injection Create README.md 2023-09-07 20:19:41 -04:00
README.md Update README.md 2023-10-23 22:22:04 -04:00

AI Security Research Resources

Langchain Resources

LLM Frameworks

AI Security Best Practices and Tools

AI Security Resources from Omar's Training Sessions

AI Ethics and Privacy Resources

Tools & Methods for Data Collection, Cleaning, and Analysis:

  • Data Collection:
    • APIs and SDKs
    • Wireless transmission

Data Cleaning:

  1. Pandas:

    • Example: Cleaning a dataset with missing values using Pandas before training a machine learning model.
    • Relevant Link: Pandas Documentation
    • Usage in HAR and AI: Pandas can be used to structure and clean sensor data, making it suitable for training AI models capable of recognizing complex patterns in human activity data.
  2. Sci-kit learn:

    • Example: Using Sci-kit learn for feature selection and removing irrelevant features from a dataset.
    • Relevant Link: Sci-kit learn Documentation
    • Usage in HAR and AI: Sci-kit learn offers various tools for data preprocessing, which is a vital step in preparing data for AI algorithms, enhancing the performance of the models in HAR applications.

Data Analysis:

  1. TensorFlow:

    • Example: Developing a deep learning model using TensorFlow to classify different activities based on sensor data.
    • Relevant Link: TensorFlow Documentation
    • Usage in HAR and AI: TensorFlow provides a comprehensive platform for developing and training AI models capable of analyzing and recognizing patterns in human activity data.
  2. Keras:

    • Example: Using Keras to create a convolutional neural network (CNN) for image recognition, an essential task in AI.
    • Relevant Link: Keras Documentation
    • Usage in HAR and AI: Keras simplifies the process of building and optimizing neural networks, a crucial component in AI, to analyze human activity data more effectively and make predictions.

Visualization and Further Analysis:

  1. Matplotlib:

    • Example: Using Matplotlib to visualize the distribution of different activities within a dataset.
    • Relevant Link: Matplotlib Documentation
    • Usage in HAR and AI: Visualization of data is essential in AI to understand underlying patterns and trends in data, aiding in the better development and tuning of models for HAR.
  2. Seaborn:

    • Example: Creating a heatmap using Seaborn to visualize the correlation between different features in a dataset.
    • Relevant Link: Seaborn Documentation
    • Usage in HAR and AI: Seaborn can enhance data visualization in AI, assisting in identifying relationships and patterns in data which can influence the development and performance of HAR models.