-
Notifications
You must be signed in to change notification settings - Fork 61
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat(hackingai): add ai/ml tools EDR detections #154
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice to see potential coverage for the command lines and network traffic!
There's not a way to exclude false-positive prone items like you called out (--disable-mlflow
etc.). I haven't tested these queries, though, to see how FP-prone those flags would be.
Web URL paths would be a cool addition but that's not supported by definition files (at least not yet)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A couple more items that I'd recommend removing to reduce the noise but otherwise looks good!
Co-authored-by: Cori Smith <[email protected]>
Co-authored-by: Cori Smith <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM! 🎉
AI development tools hunt to ensure align with company guidance:
Quick review to detect some common AI tools with vulnerabilities based on EDR data
Possible false-positive cmdline arguments for mlflow that may want to exclude but not sure if variable for that: "--disable-mlflow", "--skip-mlflow", "--skip_mlflow"
There would be additional patterns for web url path but I don't think there is a variable for it either (ex: "/ajax-api/2.0/preview/mlflow/")
Inspired from
https://protectai.com/blog/hacking-ai-system-takeover-in-mlflow-strikes-again-and-again
https://protectai.com/threat-research/november-vulnerability-report
https://docs.h2o.ai/h2o/latest-stable/h2o-docs/starting-h2o.html#multicast
https://docs.ray.io/en/latest/ray-security/index.html