Skip to content
AI

Data Poisoning

Data poisoning is an attack that manipulates the data a machine learning model is trained on, so that the trained model makes the errors the attacker chose for it.

What is Data Poisoning?

Definition

Data Poisoning is an attack on a machine learning model carried out through its training data rather than its code: the attacker inserts or alters examples so the model learns the behaviour they want. The result may be broad degradation of accuracy, or a targeted backdoor that behaves normally except on inputs carrying a specific trigger. It is hard to detect after the fact, because the artefact that misbehaves — the model — contains nothing obviously malicious, which is why defences concentrate on the provenance and validation of training data rather than on inspecting the finished model.

Role in cybersecurity

Data Poisoning plays an important role in building organizational resilience against cyber threats. Implementing appropriate mechanisms in this area is required by regulations such as NIS2, DORA and ISO 27001.

Want to Reduce IT Risk and Costs?

Book a free consultation - we respond within 24h

Response in 24h Free quote No obligations

Or download free guide:

Download NIS2 Checklist