Skip to content
Paula Livingstone writing · projects · tools

Projects

Attestable

Published on:

When probabilistic AI feeds safety-critical systems, unproven output can drive physical action unchecked. Attestable is a discipline for marking a claim's basis, so it cannot.

OT SecurityCyber-Physical AssuranceIEC 62443ProvenanceSafety CaseLLM Agents

Readings: Supply Chain and OT

5 entries

Readings on where software integrity becomes physical, and the learned OT boundary. Feeds the review chapter's fourth section.

  1. Reading: Supply-Chain Integrity and Its Limit Published on: The first of the two intertwined field surveys. Software supply-chain security is organized around transparency, validity, and separation. Its validity property establishes an unchanged, authorized artefact, not a correct or fit one, which leaves admissibility open in the field's own words.
  2. Reading: Where Integrity Becomes Physical Published on: The second field survey and the point of fusion. OT security inverts IT priorities (safety first) because its actions are physical and irreversible. It meets supply-chain integrity at the safety boundary, where the Triton case records an unverified diagnosis promoted to fact and acted on.
  3. Reading: Where Attestable Sits in OT Security Published on: A positioning entry, not another OT survey. OT security is layered perimeter defence built on Purdue zones, and it asks one question: is this crossing authorised. Admissibility is orthogonal to it, asking whether a value's basis suffices to act on. Attestable is not a perimeter layer but a gate at the cyber-physical boundary the perimeter waves values through.
  4. Reading: The Learned Perimeter Published on: OT segregation is increasingly enforced by machine learning: the boundary monitor is a learned intrusion detector or anomaly scorer, and the state estimate is guarded by ML false-data-injection detectors. But a learned perimeter emits a score, not a basis, and can be walked across by adversarial design (Random Forest and J48 accuracy fell 16 and 20 points under attack). Moving the firewall to ML relocates the admissibility gap; it does not close it.
  5. Reading: When the Model Makes the Decision Published on: When machine learning makes or shapes an OT control decision, every safeguard the field reaches for lands somewhere other than admissibility. Safe reinforcement learning constrains actions probabilistically but cannot warrant a single one; state estimation can be corrupted beneath the controller without tripping its checks; and the trust layer bolted on top is post-hoc explanation, which describes the model rather than justifying the irreversible act it triggers.