← Governance

Section 03 · Threat Modeling

OWASP foundation. AI-specific overlay.

Threat modeling for embedded AI systems must account for traditional application-layer risks, data pipeline vulnerabilities, model integrity risks, inference-time manipulation, and third-party model exposure. This framework aligns with OWASP threat categories, then extends them for AI-specific attack surfaces and maps adversarial techniques against MITRE ATT&CK and ATLAS.

Do I need to threat-model this?

Tier 1

Not required

Standard SDLC review only.

Tier 2+

Required

Documented threat model using template below.

Tier 3+

Governance review

Formal validation by central governance.

Map the system first

All threat modeling begins with a structured system map. Threats are evaluated against each component.

01

Data Sources

02

Feature Engineering Pipeline

03

Model Training / Fine-Tuning

04

Model Registry

05

Inference Layer

06

API Gateway

07

Business Logic Integration

08

Logging & Monitoring

09

Third-Party Dependencies

Core layer: OWASP application risks

These apply directly to AI APIs, feature pipelines, model registries, and training infrastructure. Treat them as the floor. The AI overlay is additive, not a replacement.

Broken Access Control
Cryptographic Failures
Injection
Insecure Design
Security Misconfiguration
Vulnerable & Outdated Components
Identification & Authentication Failures
Software & Data Integrity Failures
Logging & Monitoring Failures

AI-specific threat overlay

Ten threat categories that traditional appsec models do not cover. Categories 9 and 10 (prompt injection and indirect prompt injection) are the dominant attack surface for LLM-based systems and are where governance, IAM, and secure RAG converge.

01

Training Data Poisoning

Malicious or biased data inserted into training sets to alter model behavior, induce backdoors, or skew predictions for protected classes.

02

Feature Manipulation

Upstream manipulation of model inputs (at the feature pipeline or data source) to alter outputs without compromising the model itself.

03

Model Extraction

Attackers reconstruct model behavior, weights, or decision boundaries via repeated queries, recovering IP or enabling downstream attacks.

04

Model Inversion

Reconstruction of sensitive training data via inference queries, which can expose PII or proprietary data even when the training set is private.

05

Drift Exploitation

Deliberate manipulation of input distributions to degrade model performance over time, evade detection, or push behavior past calibration limits.

06

Automation Amplification

Model outputs trigger cascading automated decisions. Small errors compound across downstream systems before any human intervention.

07

Vendor Opacity Risk

Limited visibility into third-party model architecture, training data, or change history. The vendor changes the model; the enterprise inherits the regression.

08

Unauthorized Retraining

Shadow updates, unauthorized version swaps, or pipeline tampering that replace a reviewed model with one that bypassed governance gates.

09

Prompt Injection

LLM-era

Direct manipulation of model instructions via user input, overriding system prompts, exfiltrating context, or hijacking the model's behavior.

10

Indirect Prompt Injection

LLM-era

Adversarial payloads embedded in retrieved documents, tool outputs, or web content that hijack the model when consumed as context. The user never types the attack; the model encounters it through the supply chain. This is where governance, IAM, and secure RAG converge.

Threat modeling workflow

For Tier 2+ systems. Tier 3–4 requires governance validation.

  1. 01Map architecture
  2. 02Identify OWASP application risks
  3. 03Overlay AI-specific risks
  4. 04Assign impact score
  5. 05Define mitigation strategy
  6. 06Log in centralized risk registry

Risk scoring

Each threat is scored across exploitability, business impact, regulatory impact, model integrity impact, and automation amplification. High-risk threats require documented mitigation or formal risk acceptance, not silence.

Adversarial alignment: ATT&CK and ATLAS

For Tier 3–4 systems, identify relevant adversarial techniques from MITRE ATLAS, map potential attack paths to architecture, validate mitigations, and log technique coverage. This integrates adversarial thinking without creating research theater.

Model poisoning
ML artifact compromise
Adversarial input crafting
Model exfiltration
ML pipeline supply chain attack