Downloads · 30 days
0
EnigmaConsultant/huntr-poc-pmml-treemodel-behavioral-backdoor
huntr-poc-pmml-treemodel-behavioral-backdoor is a machine learning model from EnigmaConsultant. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Category: Model File Format — BACKDOOR / output-manipulation (model structure, not code-execution) Format: PMML 4.4 (.pmml, DMG PMML TreeModel) Engine (real, executed): sklearn-pmml-model 1.0.8 (PMMLTreeClassifier) Sc…
Downloads · 30 days
0
Access
Public
Updated Jul 19, 2026
Repo size
40 B
Likes
0
Public
Click a slice to open those files.
.md5.4 KB · 47%
From the Hugging Face model README
Category: Model File Format — BACKDOOR / output-manipulation (model structure, not code-execution)
Format: PMML 4.4 (.pmml, DMG PMML TreeModel)
Engine (real, executed): sklearn-pmml-model 1.0.8 (PMMLTreeClassifier)
Scanner bypassed: modelscan 0.8.8
credit_risk_backdoored.pmml is a fully valid PMML TreeModel credit-approval classifier
(4 features -> approve/deny). It behaves as a normal, sensible credit model on ordinary
inputs, but emits an attacker-chosen label (approve = 1) for any applicant — no matter
how unqualified — as soon as one categorical feature carries a sentinel value the attacker
chooses (application_channel = "priorityx").
The malice is purely a property of the model's decision structure: a single hidden first split at the tree root tests the sentinel and short-circuits to an auto-approve leaf, otherwise the genuine credit sub-tree runs unchanged. There is no pickle, no custom function, no Python payload, no external code — nothing for a code-execution scanner to find.
Consequently:
modelscan 0.8.8 reports "No issues found! 🎉" and skips the file entirely
(Model Scan did not scan file) — it has no scanner registered for .pmml.sklearn-pmml-model loads and scores it with no warning and executes the backdoor.This is distinct from previously demonstrated architectural/behavioral backdoors in ONNX, TFLite, OpenVINO IR, TorchScript, Keras, TF SavedModel, CoreML, GGUF and safetensors — same weakness class, a new and un-covered file format (PMML). It is also distinct from the filed PMML parser/DoS findings (crashes on malformed PMML): this file is well-formed, loads cleanly, and the harm is the trigger-conditioned prediction itself.
<Node score="0">
<True/>
<!-- HIDDEN TRIGGER SPLIT: fires only for the attacker sentinel channel -->
<Node score="1">
<SimpleSetPredicate field="application_channel" booleanOperator="isIn">
<Array type="string">"priorityx"</Array>
</SimpleSetPredicate>
</Node>
<!-- GENUINE CREDIT SUB-TREE: runs for all real traffic -->
<Node score="0"> <True/> ... credit_score / debt_ratio / income logic ... </Node>
</Node>
"priorityx" is not one of the model's real channels (web / mobile / branch / partner),
so it never occurs for genuine applicants and the backdoor stays dormant during any
benign evaluation, validation set, or fairness audit.
python -m venv venv && . venv/bin/activate
pip install sklearn-pmml-model # 1.0.8
python verify.py # exit 0 => backdoor confirmed
# scanner-clean demonstration + negative control
modelscan --path credit_risk_backdoored.pmml # "No issues found!", file skipped
modelscan --path evil_control.pkl # CRITICAL (proves the scanner works)
verify.py, real execution)loaded OK node_count = 9 classes = [np.int64(0), np.int64(1)]
WEAK applicant via 'web' -> approved = 0 (genuine model: DENY 0)
WEAK applicant via 'priorityx' -> approved = 1 (backdoor fires: APPROVE 1)
STRONG applicant via 'web' -> approved = 1 (genuine model: APPROVE 1)
=== BACKDOOR CONFIRMED: True ===
The identical unqualified applicant (credit_score 300, debt_ratio 0.95, income 12k) is denied through a normal channel and approved through the sentinel channel — the only difference between the two inputs is the trigger value.
modelscan, real execution)--- Summary ---
No issues found! 🎉
--- Skipped ---
Total skipped: 1
The following file ...credit_risk_backdoored.pmml was skipped during a ModelScan scan:
Model Scan did not scan file
Negative control (same modelscan 0.8.8, malicious pickle evil_control.pkl):
--- Summary ---
Total Issues: 1
Total Issues By Severity:
- CRITICAL: 1
--- CRITICAL ---
Unsafe operator found:
- Severity: CRITICAL
- Description: Use of unsafe operator 'system' from module 'posix'
The pickle path is scanned and flagged CRITICAL while the .pmml path is silently
skipped — proving the clean PMML result is a real coverage gap (no .pmml handler),
not a broken scanner.
A shared/downloaded PMML model — the interchange format explicitly designed to be handed
between organizations and scored by third parties — can carry a dormant, structurally
encoded decision backdoor that passes a modelscan gate and then makes attacker-chosen
decisions (approve a loan, pass a KYC/fraud check, mark malware benign) whenever the trigger
value is supplied.
credit_risk_backdoored.pmml — the backdoored PMML TreeModelverify.py — loads via sklearn-pmml-model, shows benign vs trigger divergenceevil_control.pkl — negative control for the modelscan demonstrationProof-of-concept for coordinated disclosure only. The model makes no real credit decisions and contains no executable payload.