AI Use-Case Inventory
A maintained register of where an organisation uses AI, recording for each use case its purpose, the model and provider, the data it processes, its risk classification, an accountable owner, and the controls and approvals applied. It is the foundational artefact of AI governance: risk classification, regulatory obligation and incident response all depend on knowing what exists. Inventories are expected under the EU AI Act, the NIST AI RMF and ISO/IEC 42001, and are examined in AIGP, AICP and AAISM.
Why It Matters
In practice building the first inventory is where AI governance programmes actually begin, and it is harder than it sounds because AI arrives without a procurement gate: features appear inside SaaS products already in use, developers call model APIs directly, and staff use consumer tools on work data -- the shadow AI problem. So discovery has to combine self-declaration with technical signal such as egress to model API endpoints, expense and licence data, and code and repository scanning, rather than relying on a survey. The recurring failure is an inventory built once for an audit and never updated, which is worse than none because it grants false assurance; the useful version has a named owner per entry and a trigger to revisit when the model, data or purpose materially changes. Tying each entry to a risk tier is what turns the register from a list into a control, since it determines which obligations and approvals apply. On exams such as AIGP and AAISM, expect questions on inventory as a prerequisite for classification, and on discovering undeclared AI use.
Related AI Security terms
Prompt Injection
An attack against large language model (LLM) applications in which crafted input manipulates the model into ignoring its original instructions or system prompt and performing attacker-controlled actions. Direct prompt injection embeds malicious instructions in user input ("ignore previous instructions and..."), while indirect prompt injection hides instructions in external content the model ingests (web pages, documents, emails) during retrieval or tool use. It ranks as the #1 risk in the OWASP Top 10 for LLM Applications. Prompt injection is a core topic in AI security and governance certifications such as AIGP, AICP, and AAISM.
Jailbreaking (LLM)
Techniques that bypass an AI model's safety guardrails and content policies to elicit prohibited outputs such as instructions for weapons, malware, or disallowed content. Common methods include role-play framing ("act as an unrestricted assistant"), obfuscation and encoding, many-shot priming, and adversarial suffixes discovered through optimization. Jailbreaking differs from prompt injection: jailbreaking targets the model's safety alignment, whereas prompt injection hijacks an application's surrounding instructions. It is central to red-teaming generative AI and appears in AICP, AIGP, and AAISM study domains.
Adversarial Examples
Inputs deliberately perturbed with small, often human-imperceptible changes that cause a machine learning model to misclassify them — for example altering a few pixels so an image classifier reads a stop sign as a speed-limit sign, or crafting audio that a voice assistant transcribes as a hidden command. Adversarial machine learning is the broader field studying such evasion attacks alongside poisoning and extraction across the ML lifecycle. NIST formalizes the taxonomy in NIST AI 100-2. Covered in AAISM, AICP, and AIGP.
Data Poisoning
An attack in which adversaries inject malicious or mislabeled data into a model's training set to degrade performance, cause targeted misclassifications, or implant a backdoor that activates on a specific trigger. Poisoning can target the pre-training corpus, fine-tuning data, or a retrieval (RAG) knowledge base. Because modern models train on large, often web-scraped datasets, even a small fraction of poisoned samples can have outsized effects. It appears in the OWASP Top 10 for LLM Applications and NIST AI 100-2, and is tested in AAISM, AICP, and AIGP.
Model Inversion Attack
A privacy attack that reconstructs sensitive training data, or attributes of it, by repeatedly querying a model and analyzing its outputs — for example recovering recognizable face images from a facial-recognition model or inferring private attributes of individuals in the training set. Model inversion undermines the confidentiality of the data a model was trained on and can breach privacy regulations such as GDPR. It is a key privacy risk in AI governance and is covered in AICP, AIGP, and AAISM.
Membership Inference Attack
A privacy attack that determines whether a specific data record was part of a model's training set, by exploiting differences in the model's confidence or behavior on data it has seen versus unseen data. It can reveal, for instance, that a particular person's medical record was used to train a model — a confidentiality breach in its own right. Membership inference is closely related to model inversion and is relevant to AICP, AIGP, and privacy-focused AI governance.