feat(hackingai): add ai/ml tools EDR detections #154
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
rc-csmith
requested changes
Apr 1, 2024
There was a problem hiding this comment.
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)
rc-csmith
requested changes
May 7, 2024
Co-authored-by: Cori Smith <74794990+rc-csmith@users.noreply.github.com>
Co-authored-by: Cori Smith <74794990+rc-csmith@users.noreply.github.com>
TreWilkinsRC
approved these changes
May 13, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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