ember
Elastic Malware Benchmark for Empowering Researchers (by elastic)
SOREL-20M
Sophos-ReversingLabs 20 million sample dataset (by sophos)
ember | SOREL-20M | |
---|---|---|
4 | 2 | |
899 | 596 | |
1.2% | 3.4% | |
0.0 | 0.0 | |
8 months ago | about 3 years ago | |
Jupyter Notebook | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ember
Posts with mentions or reviews of ember.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-11-21.
-
[D] Malware Detection Analysis Using Machine Learning
Your other option is the EMBER dataset, which has pre-vectorized feature vectors available to use. Unfortunately, that is also quite limiting: there isn't much you can do with the vectorized data that hasn't already been done. But it would let you work with something much bigger scale for free.
-
[Suggestions] Malware Detection Analysis Using Machine Learning
Check out ember: https://github.com/elastic/ember
- Large Benign “goodware” Samples
- Malware & deep learning
SOREL-20M
Posts with mentions or reviews of SOREL-20M.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-11-21.
-
[Suggestions] Malware Detection Analysis Using Machine Learning
And I was thinking that a really easy improvement on that project would be to run it against SoREL-20M (https://github.com/sophos/SOREL-20M) instead of versus the Microsoft dataset, that dataset is too old and too small, it is the MNIST of malware, and we should stop using it.
-
Large Benign “goodware” Samples
Another option might be to go with an existing dataset. Sophos AI and ReversingLabs teamed up recently to publish the SOREL-20M dataset, including both benign and malicious samples (partially defanged). You'll want to read their paper to understand what you're getting.
What are some alternatives?
When comparing ember and SOREL-20M you can also consider the following projects:
MalConv-keras - This is the implementation of MalConv proposed in [Malware Detection by Eating a Whole EXE](https://arxiv.org/abs/1710.09435) and its adversarial sample crafting.
fusing_feature_engineering_and_deep_learning_a_case_study_for_malware_classification
Angular - Deliver web apps with confidence 🚀