Concern 28 · Working draft · editorial review in progress
Untargeted poisoning
Untargeted poisoning is deliberate corruption of training information meant to reduce a model's general usefulness rather than cause one selected mistake.
Understanding the concern
Training examples teach a model which patterns to follow. In untargeted poisoning, someone deliberately damages those examples or their labels to make the model perform worse across a range of tasks. The changes can be carefully planned; they do not have to look like random noise.
This overlaps with availability attacks. Untargeted describes the lack of one chosen output, while availability emphasizes whether the service remains usable. Ordinary poor-quality data can have similar effects without an attacker, so intent should not be assumed from falling accuracy.
An example
A damaged answer key could confuse a whole class across many questions, rather than mislead it about just one topic.
Illustrative unless identified as a documented case.
Words in plain English
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
- Training
- The process of using examples to shape how an AI model behaves. Learning patterns from material does not establish that the material is true or fair.
- Data poisoning
- Deliberately changing training material to push a system toward unwanted behavior.
Evidence and its limits
NIST's attack taxonomy distinguishes objectives and capabilities. Falling accuracy alone does not establish an intentional attack.
NIST · 2025 · Technical report
Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations ↗ (opens in a new tab)Defines attack objectives and mechanisms across AI lifecycle stages. Taxonomy categories are not estimates of incident frequency.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Do we have evidence of deliberate interference, or only evidence that data quality has fallen?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Justice
Justice means fair treatment, fair procedures, and attention to who receives benefits and burdens. It asks whether people with less power can be heard and seek repair.
Look at outcomes across different groups and individual cases. Provide a usable way to challenge decisions and correct harm. Equal wording in a policy does not guarantee equal treatment in practice.
Ask together: Who benefits, who bears the cost, and who can challenge the decision?
Stewardship
Stewardship means caring for resources and systems that others depend on, including people who will use them later. It looks beyond the benefit of a quick launch.
Plan for maintenance, energy use, data protection, and eventual shutdown. Ask who will look after the tool when the original team moves on and how future users can avoid inheriting hidden costs.
Ask together: What are we responsible for caring for over time?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.