Risks: shared-GPU memory residue, side channels, checkpoint files that execute on load, resource exhaustion (denial of wallet), sanitisation of dense storage (use cryptographic erasure).
TEE / confidential computing = data and weights protected in use, with attestation.
Non-determinism — pin model versions, fix sampling, log everything, test repeatedly.
Uncertainty — aleatoric (data noise) vs epistemic (lack of knowledge); models are often poorly calibrated.
Drift — data (inputs), concept (input→output relationship), model (performance), behavioural (after updates). Can be adversarially induced. Major drift = reassessment trigger.
Model collapse — training on AI-generated data erodes the tails → track provenance, keep human data.
Metrics
Precision = TP/(TP+FP) — are alerts real? Recall = TP/(TP+FN) — did we catch them? F1 balances both.
Install DigiTrust on your phone for one-tap access and offline lessons.
Analytics cookies
With your permission we use Google Analytics to count visits and see which pages help learners. It sets cookies on your device and sends information about your visit to Google, which may process it outside your country. Nothing is loaded unless you accept, and you can change your mind any time under Cookie settings at the bottom of every page. How we use cookies