Critical

MONAILabel Server Crash and Silent Inference Corruption via Crafted DICOM (pydicom DS/IS Validation Bypass)

  • Disclosed: 27.10.2026
  • Updated: 28.10.2026 10:00

Summary

An unauthenticated remote attacker can crash a running MONAILabel server or silently corrupt its medical AI inference results by uploading a single crafted DICOM file (~132 KB) via the REST API. The vulnerability stems from pydicom's lack of validation for Decimal String (DS) and Integer String (IS) DICOM Value Representations, which allows NaN and infinity values to pass through MONAI's PydicomReader and propagate through the entire spatial transform and ML inference pipeline.

No authentication is required for the default MONAILabel REST API. The attacker needs only network access to the server (default port 8000).

Severity: CVSS 3.1: 8.7 HIGH
CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:N/I:H/A:L
CWE: CWE-20 (Improper Input Validation) → CWE-682 (Incorrect Calculation)

Details

Root Cause — Layer 1: pydicom accepts invalid VR values

pydicom's DSfloat.__new__() calls Python's float(val), which silently accepts "NaN", "inf", and "-inf". The DICOM standard (PS3.5 Table 6.2-1) defines DS as digits 0-9, +, -, ., e only. NaN and inf are not valid DS values. The is_valid_ds() check only runs in RAISE validation mode, which is NOT the default. The default mode is WARN, which still returns the invalid value.

python
>>> from pydicom.valuerep import DSfloat
>>> DSfloat("NaN")
nan    # Accepted silently — should be rejected
>>> DSfloat("inf")
inf    # Accepted silently — should be rejected

This affects ALL pydicom versions from 0.9.7 through 3.0.2 (current).

A related bypass exists in pydicom's IS type: IS("1e4") returns 10000 via an int(float(val)) fallback, accepting scientific notation that is not valid per the DICOM standard.

Root Cause — Layer 2: MONAI Core trusts pydicom output without validation

MONAI's PydicomReader._get_affine() builds a 4x4 affine transformation matrix from PixelSpacing, ImagePositionPatient, and ImageOrientationPatient with ZERO isfinite() or isnan() checks. NaN in PixelSpacing produces NaN in the affine diagonal, propagating through every spatial transform: PydicomReader._get_affine() → LoadImaged → Spacingd → Model → Writer

Root Cause — Layer 3: MONAILabel REST API accepts anything

MONAILabel's PUT /datastore/ endpoint accepts DICOM uploads with no authentication (default deployment), no validation of spatial metadata, and no bounds checking on any DICOM tag values. The malicious DICOM is stored permanently and made available for inference.

PoC

Environment Setup:

bash
# Start MONAILabel (Docker)
docker pull projectmonai/monailabel:latest
docker run -d --name monailabel-poc -p 8000:8000 --memory=8g \
    projectmonai/monailabel:latest monailabel start_server \
    --app /opt/monai/sample-apps/radiology \
    --studies /opt/monai/datasets/Task09_Spleen/imagesTr \
    --conf models segmentation

# Verify server is running
curl http://localhost:8000/info/

Step 1 — Establish baseline (legitimate data works):

bash
curl -X POST "http://localhost:8000/infer/segmentation?image=spleen_40" \
     -o baseline.nii.gz -w "HTTP %{http_code} - %{size_download} bytes"
# Result: HTTP 200, ~223,628 bytes valid segmentation mask

Step 2 — Run the attack (NaN DICOM upload + inference):

bash
pip install pydicom numpy requests
python poc_monailabel_ds_bypass.py --server http://localhost:8000

The PoC script:

  1. Confirms pydicom accepts NaN/inf in DS fields
    1. Creates three malicious DICOM files (~132 KB each) with NaN/inf in PixelSpacing and ImagePositionPatient
    1. Uploads each via PUT /datastore/ (no auth required) — HTTP 200 accepted
    1. Triggers inference via POST /infer/segmentation — HTTP 500, server crash

Demonstrated Results:

Payload Upload Inference Result
Baseline (spleen_40) N/A HTTP 200 Valid 223 KB segmentation
NaN PixelSpacing HTTP 200 HTTP 500 RuntimeError crash (18.0s wasted compute)
NaN PixelSpacing + IPP HTTP 200 HTTP 500 RuntimeError crash (16.7s wasted compute)
Inf PixelSpacing HTTP 200 HTTP 500 RuntimeError crash (16.4s wasted compute)

Server crash traceback:

monailabel/tasks/infer/basic_infer.py → self.writer(data)
monailabel/transform/writer.py → write_itk(...)
itk/ITKCommonBasePython.py → itkProcessObject_Update()
RuntimeError: itkGDCMImageIO.cxx:1226:
  ITK ERROR: GDCMImageIO: A Floating point buffer was passed
  but the stored pixel type was not specified.

Each request burns ~16 seconds of server compute (full ML inference pipeline) before crashing. The NaN DICOM persists in the datastore — any future inference on that image ID crashes the server again.

Library-level confirmation: 17/17 test vectors confirmed against MONAI 1.5.2 and pydicom 3.0.2, including actual MONAI LoadImaged and Spacingd transforms accepting NaN geometry without error.

Impact

  1. Denial of Service: A single ~132 KB DICOM upload crashes the MONAILabel inference pipeline. All active inference requests from legitimate users are aborted. Repeatable indefinitely with minimal bandwidth.
  2. Silent Data Corruption: NaN values in spatial metadata propagate through the entire ML inference pipeline and produce geometrically incorrect segmentation masks. If the output writer does not crash, the result is returned with HTTP 200 and zero warnings.
  3. Persistent Datastore Poisoning: The malicious DICOM is stored permanently via PUT /datastore/. Any future inference request on that image ID reproduces the crash or corruption, persisting across server restarts.

Affected MONAI Ecosystem (9 repositories):

  • MONAI Core: PydicomReader, LoadImaged, Spacingd transforms
  • MONAILabel: REST API + DICOMweb datastore
  • MONAI Deploy App SDK: DICOMDataLoaderOperator
  • model-zoo, VISTA, GenerativeModels, tutorials, research-contributions

Affected DICOM Tags (any DS VR): PixelSpacing, ImagePositionPatient, SliceThickness, ImageOrientationPatient, RescaleSlope, WindowCenter/WindowWidth

Recommended Fix:

  1. Add math.isfinite() validation in PydicomReader._get_affine() on all values from PixelSpacing, IPP, IOP. Raise ValueError for NaN/inf.
    1. Validate spatial metadata of uploaded DICOM in MONAILabel PUT /datastore/. Return HTTP 400 for invalid geometry.
    1. Validate spatial metadata is finite in LoadImaged/Spacingd before resampling.
    1. Coordinate with pydicom upstream to reject NaN/inf in DS fields in all validation modes.

Upstream: pydicom GHSA filed 2026-04-05.

Author: Paulino Calderon (paulino@calderonpale.com)

What to do

Upgrade MONAI to version 1.6.1 or later.

Recommended mitigations from the source:

  • Add math.isfinite() validation in PydicomReader._get_affine() on all values from PixelSpacing, IPP, IOP, raising a ValueError for NaN/inf.
  • Validate spatial metadata of uploaded DICOM files in MONAILabel PUT /datastore/, returning HTTP 400 for invalid geometry.
  • Validate that spatial metadata is finite in LoadImaged/Spacingd before resampling.
  • Coordinate with pydicom upstream to reject NaN/inf in DS fields across all validation modes.

Affected software

Click a technology to see all vulnerabilities affecting it.

PlatformPackageVulnerable versionsFixed in
Python (PyPI) monai < 1.6.1 1.6.1

References

CVSS score 9.3/10
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:N/I:H/A:L
Weakness (CWE)
CWE-20
Platform
Python (PyPI)
Package
monai
Disclosed
27.10.2026
Updated
28.10.2026 10:00

Sources and licenses · Edited or translated by DockRay; source rights and applicable licenses are retained.

OSV / GitHub Advisory Database - GHSA-6hp3-vr39-rqw8 - CC BY 4.0

Vulnerability history: monai

All published vulnerabilities of this package (Python (PyPI)), newest first. Shows whether this is a one-off slip or a package that needs watching.

All (12) in the archive
Total entries
12
First → latest
09.2025 10.2026
Without a fix
1
Exploited in attacks
0

Severity breakdown

  • Critical 1
  • High 8
  • Medium 1
  • Unrated 2

Disclosures per year

  1. 2025: 3
  2. 2026: 9
Severity:
  1. MONAILabel Server Crash and Silent Inference Corruption via Crafted DICOM (pydicom DS/IS Validation Bypass) this entry
    Critical · 9.3 CVE-2026-48705 < 1.6.1 1.6.1
  2. High CVE-2026-100844 < 1.6.0 1.6.0
  3. High · 7.6 CVE-2026-100846 < 1.6.0 1.6.0
  4. High · 8.8 CVE-2025-58757 < 1.5.1 1.5.1
  5. High · 8.8 CVE-2025-58756 < 1.5.1 1.5.1

Know which vulnerabilities affect your application

With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.

Connect your application
DockRay newsletter

Application security in your inbox

Important vulnerabilities, actionable guidance and practical advice for your applications. Choose your technologies and follow what matters to your project.

  • A daily digest of new vulnerabilities, critical ones included.
  • Notifications about important updates.
  • Practical advice on application security and monitoring.

Leave empty to receive updates for every technology.

Free to subscribe. Unsubscribe with one click in any email.