TISAX Assessment Consulting × AI attack defence

TISAX and AI attacks: threat modelling vehicles and OEM data

Updated 2026-11-10

The short answer

AI threat modelling for automotive products belongs in the ISO/SAE 21434 TARA: list perception models, voice assistants and model files shipped over the air as assets and cover adversarial examples, model poisoning, prompt injection and model theft. UN R155 Annex 5 is a minimum threat list, so AI threats have to be added. TISAX covers the organisation: OEM confidential, prototype and test data may enter AI tools or training pipelines only with approval by classification and with records kept.

Companion page: service overview: TISAX Assessment ConsultingWhat this service is, who it is for and what we deliver are on the service overview page.

TISAX covers the organisation, so where does threat modelling for AI attacks on vehicle products belong?

Many automotive suppliers treat TISAX as the place where all security lives, but TISAX assesses how a company protects OEM information, prototypes and data, not the security engineering of the product itself. AI attacks therefore have to be handled on two layers:

  • Product layer: AI functions in ECUs, cockpit systems, ADAS perception and connected-vehicle back ends are modelled through the ISO/SAE 21434 threat analysis and risk assessment (TARA, the methods in clause 15). Vehicle manufacturers need a UN R155 cyber security management system (CSMS) and type approval and usually extend TARA requirements to suppliers.
  • Organisation layer (TISAX): engineers using generative AI tools on OEM drawings, specifications, prototype photos and test data, or training models on fleet data, are handling OEM confidential information and fall within the TISAX assessment scope.
  • Functional safety: ISO/PAS 8800:2024 addresses safety risks from output insufficiencies and systematic errors of in-vehicle AI elements. It complements the 21434 security analysis and does not replace it.

Use one asset inventory and one threat vocabulary (the NIST AI 100-2 attack classes) for both layers so the story holds together in audits.

Which AI attacks should go into the TARA for a vehicle product?

UN R155 Annex 5 lists the threats and mitigations a vehicle-type risk assessment must at least consider; it is a minimum list, and threats specific to AI elements have to be added in the TARA. The table shows what we recommend assessing as a minimum:

AI attackEntry point in the vehiclePossible consequenceReference
Adversarial examples / evasionCamera, radar and lidar perception input; deliberately altered road signsWrong object recognition, wrong ADAS decisionsNIST evasion attacks
Model poisoning, data poisoningFleet data uploads, labelling suppliers, pre-trained modelsBackdoored model or failure in specific situationsNIST poisoning; OWASP LLM04
Model file tamperingOver-the-air updates, diagnostic interfaces, flashing toolsMalicious or outdated model installedR155 Annex 5 (update procedure threats); UN R156 software update management
Prompt injectionCockpit voice assistants, in-vehicle AI that reads messages or web contentUnauthorised vehicle functions triggered, owner data exposedNIST prompt injection; OWASP LLM01, LLM06
Model theft, training data extractionModel files in the vehicle, cloud inference APIsSupplier's core model or owner data exposedNIST privacy attacks; OWASP LLM02
Back-end resource abuseConnected-vehicle cloud AI servicesOutage, runaway costOWASP LLM10

How do AI threats fit into the ISO/SAE 21434 TARA?

No separate AI process is needed. Add four things to the existing TARA:

  1. Asset identification: list model files and versions, training data sources, labelling suppliers, inference endpoints and prompts as assets, with their confidentiality, integrity and availability needs.
  2. Threat scenarios: apply the attack list above to each AI asset and write scenarios of the form: attacker, interface, action, damage.
  3. Attack feasibility and impact rating: rate with the 21434 method; judge the impact of adversarial examples and perception failure together with the functional safety team (ISO 26262, ISO/PAS 8800).
  4. Treatment and verification: map each scenario that needs treatment to a cybersecurity goal and a control and schedule tests; redo the TARA when the model is updated, retrained or sourced from a new supplier.

The TARA documents and CSMS evidence an OEM asks for can then cite these records directly.

On the TISAX layer, which controls and evidence are needed before OEM data enters an AI tool?

Requirements are those in the TISAX documents published by ENX and the VDA ISA. The table shows how we place AI use cases inside existing information security requirements; it does not quote ISA control numbers.

SituationControlEvidence
Engineers paste OEM drawings or specifications into an external generative AIDefine by classification which levels may go into which AI services; confidential and prototype data only into approved enterprise or on-premises modelsAI use policy, approved service list, gateway block logs
The AI service is an external IT serviceAssess the supplier before use: training on customer data, storage location, retention, incident notificationSupplier assessment, contract clauses
Training models on fleet or test dataAccess control on the training pipeline, records of data source and purpose; check the OEM contract allows itData flow diagram, authorisation records
Prototype photos and test imagesExtend prototype protection to AI labelling and image tools; no uploads to unapproved platformsLabelling supplier contracts, access logs
Accounts and usagePersonal accounts, disabled on leaving, abnormal usage alertsAccount list, alert records

Who does what across product security, information security, R&D and suppliers, and which part do Winners take?

  • Product security (CSMS) team: maintain the AI attack list, bring AI threats into the TARA and answer the OEM's cybersecurity interface agreement requirements.
  • Information security (TISAX) team: set the AI use policy and approved list and handle access control and records for AI tools and OEM data.
  • R&D and AI team: provide model, data source and update process information; a model release triggers reassessment.
  • Procurement: agree data use limits and incident notification with AI service, labelling and model suppliers.

Winners Consulting determines TISAX scope and assessment level, brings AI use cases into the information security system, and helps product teams set up a TARA method that includes AI threats, with evidence planning. We advise only and do not perform TISAX assessments; assessments are carried out by audit providers recognised by ENX.

Already holding a TISAX label: where do you start with AI threat modelling?

  1. Build two inventories: the AI components in your products, and the AI tools staff actually use (including personal accounts).
  2. Control the data exits first: decide which AI services may receive OEM confidential and prototype data, and block unapproved services.
  3. Extend the TARA: pick one product with AI features, run a TARA round with the attack list on this page, turn it into a template and roll it out to other products.

These records are then ready for the next TISAX assessment or OEM audit.

AI attack defence for other services

Official sources

Ask a consultant on LINE

No forms: the button opens LINE with the page you are reading filled in. Send it and a Winners Consulting consultant will reply. The first diagnosis is free.

Winners Consulting track record

Winners Consulting Services is a Taiwan RegTech platform provider and enterprise risk management consultancy.

Trusted long-term by 20+ companies, we work as an industry-focused, long-term partner to our clients.

Named client engagements, published with client permission:

See case studies

TISAX and AI attacks: threat modelling vehicles and OEM data