EMBER training set: malicious and benign samples?

Open
#39 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
3/5
Estimated time
1-2 days
Newbie friendliness
25/100
Issue type
Documentation
Clarity
Needs clarification
Activity status
Stale
Tech stack
python
Domain
machine-learning

Research direction

Review the repository documentation and the EMBER training and labeling setup to determine whether both malicious and benign samples are used and how importance labels are assigned. Done means documenting that distinction clearly for research users.

Written by the indexing model from the issue text.

Description

Hi! Is this trained on both malicious and benign samples from the EMBER set? Unclear from the documentation whether the weak supervision of importance labels comes from exclusively malicious distributions. Using this tool in a research setting where this is a potentially important distinction.

Thanks!

Dominant language
Python
Stars
763
Forks
126
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from mandiant/stringsifter

All issues in mandiant/stringsifter

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.