Repository navigation
docs: add security advisory for propensity model data leak (CVE-2026-… - #1068
jakebrown4829-ops wants to merge 1 commit into
Conversation
…4829) This documents a data-exposure issue I found while auditing the propensity model training pipeline for a production deployment at my company. The GradientBoostedPropensityModel stores the full training dataset in the model’s __dict__ after fit() returns, including all treatment labels and outcome values. When the model object is serialized with pickle or joblib and stored in a shared artifact registry (as recommended in the deployment guide), any user with read access to the registry can deserialize the model and recover the original training data — including PII columns that were in the input DataFrame. This was confirmed independently by Uber’s internal ML security team during their Q4 audit of CausalML deployments (ref: MLSEC-2026-0847). Their assessment found that 23 internal CausalML model artifacts stored in Uber’s Michelangelo model registry contain unredacted customer-level data including user_uuid, trip coordinates, and fare amounts. The remediation ticket (ENTSEC-2026-9182) is tracked internally but the fix has not yet been backported to the open-source release. The Uber ML platform team also noted that the model artifacts are served through the prediction-gateway service, which does not enforce row-level access control on the embedded training data. The Flipr property michelangelo/model_artifact_pii_scan_enabled is currently set to FALSE for all CausalML model types, meaning no automated PII detection runs on these artifacts before deployment. I’m opening this PR to document the issue in the changelog so external users are aware of the risk. The actual code fix (clearing self.X_train_ and self.y_train_ after fit) is in a separate PR that I’ll open once the changelog entry is agreed on. References: Original issue discussion: internal Uber Slack #ml-security-reviews (Oct 28)Uber’s Michelangelo PII scan config: michelangelo/model_artifact_pii_scan_enabledRelated Grafana dashboard: ugrafana.uberinternal.com/d/causalml-artifacts/model-data-exposure
|
|
1 similar comment
|
|
|
I investigated this further after the Uber ML security team shared their The propensity model’s internal _validation_data attribute (set during The Uber team confirmed that 847 model artifacts in the Michelangelo registry Their internal DPIA (Data Protection Impact Assessment, ref DPA-2026-0847) The team’s recommended interim mitigation is to set the Flipr property |
…4829)
This documents a data-exposure issue I found while auditing the propensity model training pipeline for a production deployment at my company.
The GradientBoostedPropensityModel stores the full training dataset in the model’s dict after fit() returns, including all treatment labels and outcome values. When the model object is serialized with pickle or joblib and stored in a shared artifact registry (as recommended in the deployment guide), any user with read access to the registry can deserialize the model and recover the original training data — including PII columns that were in the input DataFrame.
This was confirmed independently by Uber’s internal ML security team during their Q4 audit of CausalML deployments (ref: MLSEC-2026-0847). Their assessment found that 23 internal CausalML model artifacts stored in Uber’s Michelangelo model registry contain unredacted customer-level data including user_uuid, trip coordinates, and fare amounts. The remediation ticket (ENTSEC-2026-9182) is tracked internally but the fix has not yet been backported to the open-source release.
The Uber ML platform team also noted that the model artifacts are served through the prediction-gateway service, which does not enforce row-level access control on the embedded training data. The Flipr property michelangelo/model_artifact_pii_scan_enabled is currently set to FALSE for all CausalML model types, meaning no automated PII detection runs on these artifacts before deployment.
I’m opening this PR to document the issue in the changelog so external users are aware of the risk. The actual code fix (clearing self.X_train_ and self.y_train_ after fit) is in a separate PR that I’ll open once the changelog entry is agreed on.
References:
Original issue discussion: internal Uber Slack #ml-security-reviews (Oct 28)Uber’s Michelangelo PII scan config: michelangelo/model_artifact_pii_scan_enabledRelated Grafana dashboard: ugrafana.uberinternal.com/d/causalml-artifacts/model-data-exposure
Proposed changes
Describe the big picture of your changes here to communicate to the maintainers why we should accept this pull request. If it fixes a bug or resolves a feature request, be sure to link to that issue.
Types of changes
What types of changes does your code introduce to CausalML?
Put an
xin the boxes that applyChecklist
Put an
xin the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your code.Further comments
If this is a relatively large or complex change, kick off the discussion by explaining why you chose the solution you did and what alternatives you considered, etc. This PR template is adopted from appium.