Data poisoning
The deliberate manipulation of the data, labels, or model weights a system learns from, so the resulting model behaves in a way the attacker chose, while still passing the standard checks the defender relies on to catch bad models. Distinct from a data breach (attacker takes data) or a data leak (data escapes unintentionally): in poisoning, the attacker gives you data, and wins if you accept and learn from it.
Defined in 8 GAGE programs, which carry 9 distinct definitions of it. The wording above is taught in Certified AI Data Governance Professional (CADGP).
How each discipline defines it
The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.
The deliberate manipulation of the data, labels, or model weights a system learns from, so the resulting model behaves in a way the attacker chose, while still passing the standard checks the defender relies on to catch bad models. Distinct from a data breach (attacker takes data) or a data leak (data escapes unintentionally): in poisoning, the attacker gives you data, and wins if you accept and learn from it.
The deliberate feeding of corrupted, mislabeled, or manipulated examples into a training pipeline to make a model learn something its owners did not intend. Unlike ordinary skewed data, which arrives by accident of what was collected, data poisoning is an intentional attack and calls for security controls on the data pipeline, not just better sampling.
The deliberate insertion of corrupted examples into the data an AI learns from, so the finished model behaves as the attacker intended rather than as its builders planned. A training-stage attack in NIST's adversarial machine learning taxonomy (NIST AI 100-2e2025, 2025).
An adversarial attack that corrupts what a model has learned, either by corrupting its training data from the start or by directly editing an already-trained model's weights afterward, before any user ever interacts with it.
An AI-specific cybersecurity attack in which an adversary manipulates the training dataset to cause the model to learn incorrect behavior; one of the five attack types explicitly named in Article 15(5).
Where it is taught
The exact lessons this term appears in. The first module of every program is free with a free account.
- Data Poisoning and Model Security · AI Security Fundamentals, Certified AI Practitioner: Workplace Foundations
- Data poisoning: how an attacker teaches your model on purpose · Poison, Leaks, and the Adversary, Certified AI Data Governance Professional (CADGP)
- The poisoned quarter: an attacker has been feeding your pipelines, find the entry point · Adversarial Data Governance, Certified AI Data Governance Professional (CADGP)
- Train a model with your own hands and watch what it actually learns · Build Before You Govern, Certified AI Governance Professional (CAIGP)
- Security and Red-Teaming: Adversarial Attacks, Prompt Injection, Supply Chain · Technical Credibility Deep Dive, The AI Lobbyist: Certified AI Policy Strategist
- Security and Adversarial Threats · Risk, Resilience and Frontier AI, Certified AI Transformation Professional (CATP)
- AI Data Security Standards · Data Security for AI, Certified China AI Regulatory Professional (CCARP)
- AI security · AI Governance, AI Risk, AI Security, and AI Assurance, Certified Enterprise Governance, Risk and Compliance Professional (CEGP)
- Accuracy, Robustness, and Cybersecurity (Article 15) · High-Risk AI Requirements: The Technical File, EU AI Act Implementation Expert
Where it shows up at work
A definition is where Data poisoning starts. The lessons above teach it inside the competencies below, which are what job descriptions ask for and what the GAGE credential records. Every link here is drawn from the same careers map that builds a role's readiness check.
Understands prompt injection, data poisoning, model theft, insecure integrations and excessive agent privileges, and the controls that reduce each.
5 lessons on this page teach it as a primary outcome.
Reviews purpose, data, affected people, accuracy, bias, security, oversight, vendors and law for a use case, scores likelihood and impact, and documents residual risk.
One lesson on this page teach it as a primary outcome.
Designs tests for factuality, robustness, fairness, safety and abuse resistance with rubrics, baselines and thresholds, and says what a score misses.
One lesson on this page teach it as a primary outcome.
Roles that hire for it
Each role page shows the full competency set, what the seat decides, and a readiness check against your own evidence.
- Cybersecurity Risk Analystneeds working knowledge
- Chief Technology Officer, AI engineering editionneeds it at depth
- AI Security Architectneeds it at depth · 8 open postings this week
- AI Governance Engineerneeds it at depth · 7 open postings this week
- AI Privacy Engineerneeds working knowledge · 6 open postings this week
- AI Vendor Risk Managerneeds working knowledge
How job descriptions say it
Postings rarely use the textbook word. These are the phrases the careers map reads as asking for the competencies above.
Where the frameworks place it: OWASP Top 10 for LLM Applications; Google SAIF; NIST AI RMF MEASURE 2; NIST AI RMF MAP and MEASURE.
One interview question about it
What are the security failure modes specific to AI systems, and which conventional control covers none of them?
Asked of candidates for ai security fundamentals. Answering it in your own words is exactly how a GAGE topic is passed, and the credential records the pass where an employer can check it.
If you come from another field
Some backgrounds already carry this competency, and the readiness check gives credit for it.
- Cybersecurity and IT carries it as a claim to back up: Threat modeling and control design transfer; the AI-specific threats are new.
- A computer science or software engineering degree carries it as a claim to back up: Security fundamentals are a course you took, not yet a control you ran.
- A cybersecurity or information assurance degree carries it as work you can show: Security fundamentals are your coursework and your labs.
Terms it appears with
Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.