Medical Device Penetration Testing for Imaging AI & SaMD
Penetration testing for imaging AI and SaMD - DICOM ingestion, model inference paths, cloud APIs, and PACS integration. FDA-aligned for AI/ML SaMD submissions.
Aligned to FDA's February 3, 2026 premarket cybersecurity guidance.
Imaging AI and SaMD devices are software products that present as cloud services or PACS-integrated workstations, and their attack surface is mostly cloud, mostly DICOM, and mostly model-adjacent. The naive pen test treats them as web apps. The right pen test treats them as a pipeline: DICOM in → preprocessing → model inference → results out → PACS / EHR. Each hop has its own failure modes, and your submission should be ready to see the whole pipeline modeled.
We test the DICOM ingestion path for malformed-tag handling (a frequent source of imaging vulnerabilities), C-STORE vs. STOW-RS authentication, and whether the de-identification step can be bypassed. On the model side we evaluate the inference path for adversarial-input behavior at the boundaries that matter clinically (not academic adversarial examples - clinically plausible perturbations the device must reject or flag), prompt-injection-style bypasses for any LLM-augmented reporting, and whether confidence/uncertainty outputs can be manipulated to suppress flags. We test cloud APIs for tenancy isolation across hospital customers, service-account scope creep, and storage permissions on intermediate buffers. Finally, the results-write path: how does the device write back to PACS, who can spoof results, and what audit trail survives a compromise? Findings are mapped to ANSI/AAMI SW96.
Layers we exercise in this engagement
The imaging & ai/samd system, from the outermost cloud and clinician surfaces down to the device itself. Highlighted layers are exercised by this medical device penetration testing services.
- 01Hospital PACS
- 02Ingress DICOM listener Tested
- 03Inference container Tested
- 04Model weights Tested
- 05DICOM SR writeback Tested
- 06Clinician web UI Tested
Layers shown outermost (top) to innermost (bottom). Dashed rows are part of the surrounding system but out of scope for this view.
Medical Device Penetration Testing Services engagement, end to end
Four phases, fixed fee, scoped to imaging & ai/samd architecture from kickoff onward.
- 01
Scope + kickoff
Architecture review, attack-surface walkthrough, and threat-model alignment with your team. A written proposal within 24 hours.
- 02
Threat-model alignment
Every STRIDE entry in your threat model is matched to a planned test case so reviewers see one-to-one coverage.
- 03
Test execution
Device, cloud, mobile, BLE/RF, and OTA channels exercised in parallel by senior engineers - not a single web-app scan.
- 04
Submission-formatted report plus retest
eSTAR-format report with findings, CVSS 4.0 scores, remediation, and retests until every finding with uncontrolled risk is closed.
Findings we test for
Attack paths that can affect imaging & ai/samd systems.
Shared inference cache can leak data across tenants
Inference results keyed only by a hash of pixel data can expose one hospital's results to another hospital using the same study, such as a phantom QA study.
DICOM C-STORE can be accepted without TLS or authentication
An on-premises appliance can expose a default DICOM AE on port 104 with no association-level authentication. A host on the hospital VLAN can push studies into the inference queue.
Model output writeback to PACS can accept a spoofed source
DICOM SR (Structured Report) writeback can use a fixed AE title for the AI device. A host that takes that AE title can push fabricated AI findings to the radiologist worklist.
Crafted metadata can suppress confidence flags
Specific combinations of acquisition metadata can cause the model to short-circuit and emit maximum-confidence 'normal' without inference. Model-card behavior can have an undocumented security implication.
Inference-worker S3 IAM permissions can be too broad
An inference worker's cloud role can grant access to an entire studies bucket instead of the current job's files. A compromised worker can read other customers' pending studies.
Public imaging & ai/samd cybersecurity history
Recalls, CISA ICS-MA advisories, and disclosed research that shape what reviewers ask about in this segment - and what our scope is built to cover.
- Independent research·2019
DICOM protocol preamble / file format research (PE-in-DICOM)
Researchers demonstrated executable code could be embedded in DICOM file preambles, surviving PACS ingestion. Reinforced the need to treat the DICOM listener as a hostile-input boundary, not a trusted intra-hospital protocol.
- NVD·2020-2024
Orthanc and DICOM toolkit CVEs
A steady stream of CVEs in open-source DICOM toolkits commonly embedded in imaging-AI containers. Drives the need for an accurate SBOM plus documented vulnerability dispositions, not a one-time pen test alone.
Blue Goat's analysis of recent DICOM toolkit advisories
"Blue Goat Cyber takes the burden off our engineers and makes FDA cybersecurity requirements easy to understand. Their expertise and smooth process mean we can focus on our product, not the paperwork. The organized documentation, perfectly formatted for eSTAR, saves us countless hours."
Standard Medical Device Penetration Testing Services deliverables
The same deliverables the parent Medical Device Penetration Testing Services service ships with - tuned to your imaging & ai/samd architecture.
- Device, firmware, and embedded testing: hardware teardown, JTAG/UART/SPI bus access, firmware extraction and reverse engineering, and exploitation of the secure boot, debug, and update paths. Done by operators who have tested infusion pumps, monitors, surgical robots, and implantables.
- Companion app and cloud API coverage: iOS/Android binary analysis, BLE pairing/GATT attacks, REST/MQTT/gRPC fuzzing, authentication and authorization testing, and tenant-isolation checks. We test the device as patients and clinicians actually use it, not in isolation.
- penetration test reports structured for FDA premarket submissions: executive summary, methodology, CVSS-scored findings tied to your threat model, reproduction steps, and documented tester independence, scope, methods, and results. Reviewer-ready, not a generic IT security PDF.
- Remediation guidance and re-test included: written fix recommendations per finding, engineer-to-engineer support during remediation, and unlimited retests until every finding with uncontrolled risk is closed, inside the fixed fee. Accepted residual risks remain documented in your risk file.
What lands in your eSTAR submission
Documents structured for the cybersecurity attachments of your submission - no reformatting on your side.
- Device, firmware, and embedded testing: hardware teardown, JTAG/UART/SPI bus access, firmware extraction and reverse engineering, and exploitation of the secure boot, debug, and update paths. Done by operators who have tested infusion pumps, monitors, surgical robots, and implantables.
- Companion app and cloud API coverage: iOS/Android binary analysis, BLE pairing/GATT attacks, REST/MQTT/gRPC fuzzing, authentication and authorization testing, and tenant-isolation checks. We test the device as patients and clinicians actually use it, not in isolation.
- penetration test reports structured for FDA premarket submissions: executive summary, methodology, CVSS-scored findings tied to your threat model, reproduction steps, and documented tester independence, scope, methods, and results. Reviewer-ready, not a generic IT security PDF.
- Remediation guidance and re-test included: written fix recommendations per finding, engineer-to-engineer support during remediation, and unlimited retests until every finding with uncontrolled risk is closed, inside the fixed fee. Accepted residual risks remain documented in your risk file.
Standards that apply
The Imaging & AI/SaMD baseline, plus the call-outs that matter for medical device penetration testing services in this segment.
Segment-specific call-outs
FDA AI/ML PCCP guidance
Your Predetermined Change Control Plan is a security boundary, not just a regulatory one. We check that the model-update path can't be hijacked to ship an unapproved model under cover of an approved PCCP change.
DICOM PS3.15 (Security Profiles) and ANSI/AAMI SW96
DICOM defines security profiles in PS3.15. Check whether your product enables them.
What's not in scope
We scope tightly on purpose. These items are either out-of-scope by design or belong in a separate engagement - we'll tell you up front, not after kickoff.
- Hospital enterprise IT network penetration testing
- Clinical efficacy or human-factors validation
- Physical security of manufacturing sites
- Source-code review (unless explicitly added as a separate engagement)
Medical Device Penetration Testing Services for Imaging & AI/SaMD - FAQs
The questions buyers in this segment actually ask before scoping a medical device penetration testing services engagement.
Go deeper on Imaging & AI/SaMD and premarket
A practical, ungated buyer's guide for medical device manufacturers evaluating cybersecurity partners, what goes wrong, why it costs you, and what to demand from your next engagement. Aligned to the FDA February 2026 premarket guidance.
The most common high- and critical-severity findings we surface in medical device penetration tests, what each one looks like in the field, and how to fix it before your FDA submission.
A practical, ungated guide to the threat modeling gaps that trigger FDA cybersecurity questions in 510(k), De Novo, and PMA submissions - and exactly how to close them before reviewers find them.
Medical device cybersecurity should scale with device risk. Christian Espinosa argues why meeting only the Section 524B minimum leaves patients and submissions exposed.
VEX resources for medical device teams: a document guide, SBOM comparison, and common assessment mistakes, with evidence-based status and regulatory context.
Medical device cybersecurity for nanotech neurostimulation: a fictional STRIDE threat model linking controller risks, patient harms, controls, and testing.
Other engagements for Imaging & AI/SaMD
Teams in this segment commonly bundle these alongside medical device penetration testing services.
Keep going
Scope a Medical Device Penetration Testing Services engagement for your imaging & ai/samd program.
A 30-minute discovery call with Christian Espinosa, Founder and CEO, and Kristy Kennedy, VP of Sales.