# Adversarial threats

Inputs, training data, updates and supply paths built to change what a model does. A research area, not a product.

> **Research area.** This is a research area, not a product. Where it mentions Vraelis Contour, it says what exists in the experiment and what is proposed.

## What we study

Separate the attack from the conditions.

- **Which path does the attack use?:** Sensor input, training data and model file each need their own threat model.
- **Where does a release check stop?:** It shows a release changed, not model provenance: where the approved bytes came from.
- **What belongs in the baseline?:** Lighting, viewpoint, normal variation and sensor faults, so ordinary conditions are not read as attacks.
- **Is it drift or an attack?:** An anomaly is a reason to investigate, not proof of an attack.
- **What does a countermeasure cost?:** Latency, memory and compute on the edge, plus misses and false alarms.

## What exists today

Research direction, with no product claim.

Nothing Vraelis has built tests, detects or blocks these attacks. No detector, no measured result.

The one overlap is the supply path: unauthorized changes, a wrong destination or changed components, are specified as scripted fault tests, not run. That does not cover manipulated inputs or poisoned training data.

## What is still open

- **Which threats matter where:** A vehicle and a control room face different attackers.
- **Adaptive testing:** Fixed examples overstate a countermeasure.
- **Reproducible results:** Model version, attacker access, input path and expected outcome.
- **One record for both:** Release and input evidence in one ordered record.

## How it connects to Vraelis Contour

Informs: Which supply paths a release check covers.

On vraelis.com: [Adversarial threats](https://vraelis.com/research/adversarial-threats), [Defense](https://vraelis.com/applications/defense), [Autonomous systems](https://vraelis.com/applications/autonomous-systems).

- [Model integrity](https://docs.vraelis.com/model-integrity): Whether the model that runs is the model that was approved.
- [Machine trust](https://docs.vraelis.com/machine-trust): Explicit identity, limited permissions and checks at execution boundaries.
- [Security evidence](https://docs.vraelis.com/security-evidence): Records a person can read, kept in order, including what could not be confirmed.

---

Vraelis documentation, Research. https://docs.vraelis.com/adversarial-threats