Cyber-physical security

Catch what is protocol-valid but physically impossible

Signature-based tools pass any command that matches an allowed pattern. MW distance works differently: it checks whether the resulting trajectory stays on the learned map of physically consistent states. A command can be valid and still drive the system somewhere physics says it should not go.

Our detection

MW distance catches what signatures can’t

False negative

Signature-based detection

A command matches an allowed pattern, so it passes every check. If the attacker stays inside the rules, nothing fires.

True positive

MW distance

The command may be valid, but the resulting trajectory falls off the learned physical manifold. The distance spikes, and that is the signal.

Red-team simulation

Your architecture, attacked in a digital twin

The digital twin runs on Podman-isolated containers with a Python physics core. We simulate an attack on a model of your architecture in a fully sandboxed environment, so your defences are tested before an adversary does it.

  1. Isolated container
  2. Physics core (Python)
  3. Attack scenario replay
  4. MW distance report
Where it applies

Sectors

  • Energy storage
  • EV charging infrastructure
  • Smart grid
  • Defence

See what your own battery data is telling you.

Share a BMS/CAN log. We run it through the MW Battery Engine and send back an MW Battery Assessment Report: findings, how sure we are, and what to do next. The first assessment is free.