#
shell-command-classifier
Here is 1 public repository matching this topic...
An experiment in backdooring a shell safety classifier by planting a hidden trigger in its training data.
python linux ai-safety machine-learning-security backdoor-attacks numpy-implementation data-poisoning adversarial-ml agentic-ai-security shell-command-classifier
- Updated Aug 21, 2026
- Python
Improve this page
Add a description, image, and links to the shell-command-classifier topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the shell-command-classifier topic, visit your repo's landing page and select "manage topics."