Inquiry about data preprocessing
Hey
@isaacwilliam4
, I am working on a similar project where i aim to leverage deep learning for analyzing network logs and detecting security incidents. I am trying to understand the specifics of how the log data from the AIT dataset was prepared for training with your model. Could you elaborate on the preprocessing steps involved? Were there any particular techniques or methods you found effective in preparing the log data for the model? Your insights would be invaluable in helping me overcome some difficulties I've encountered in data preprocessing.
As I am encountering some challenges in fully comprehending the dataset and its structure, any additional resources, documentation, or tips you could provide would be greatly appreciated.
Hey Yasir,
We did have to engineer the data to fit our model. The data is multi-labeled which can make it difficult to understand. If you send me your email I can send you the csv of the preprocessed data (672 MB) that has the log lines and their associated labels.
- Isaac
Hey @isaacwilliam4 , thank you for your quick response. My email is : [email protected] ,If you have any additional resources or tips, I would greatly appreciate them