Comments (5)
I have the same question...
from secml_malware.
Hello!
Thank you for using SecML Malware!
Which attacks you would like to run? White-box or black-box?
Black-box attacks are easy-peasy: just implement a CWrapperPhi
for your classifier, and you're done.
For whitebox, I now support only deep models implemented in Pytorch, so you should write a wrapper similar to the one I coded for MalConv.
Let me know!
from secml_malware.
from secml_malware.
For blackbox attacks, you just have to use that class (have a look at the Ember CWrapperPhi to understand how it works, for both reduced EMBER and the N-Gram.
For whitebox attacks on N-grams, I suggest you to first consider this: n-gram in not and end-to-end model, but a feature extraction. So, when you compute gradients, you end up calculating the gradient of a particular N-gram, not the single byte. Hence, for computing gradient-based attacks on n-gram, you should define a mapping between the manipulation and the these features.
So, when you compute gradients, you can decide how to map that for your classifier as well.
I suggest you reading one of the papers I wrote about that, it describes the framework and this distinciton between "input space" and "feature space" attacks.
from secml_malware.
Closing now, as the issue is more a documentation thing.
I might add a tutorial on that, when I'll have some spare time!
And please consider opening a pull-request if you manage to do this, so I can reason about merging the added models to it!
from secml_malware.
Related Issues (20)
- How to run lightGBM and SOREL model using secml_malware? HOT 2
- No data preprocessing for SorelNet? HOT 2
- Error while running the sample attack code from blackbox_tutorial.ipynb HOT 4
- real sample generation HOT 5
- can't attack EMBER model HOT 1
- Confidence on Microsoft Malware Classification Challenge HOT 10
- Differences Between WhiteBox Attacks HOT 7
- Adding support for QuoVadis models HOT 2
- AttributeError: 'NoneType' object has no attribute 'dos_header' HOT 4
- No such file or directory: 'secml_malware/data/malware_samples/test_folder' HOT 3
- lightGBM and SOREL model weights? HOT 1
- Support for ensemble models HOT 1
- SOREL ATTACK HOT 1
- CGammaSectionsEvasionProblem attack budget HOT 6
- FGSM Attacking Running for days HOT 1
- Train models HOT 5
- Fix numpy retrocompatibility for CClassifierEmber
- issue installing secml-malware with pip with python 3.12
- Wrong ember prediction
- GAMMA section injections might load sections at random
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from secml_malware.