Concern 26 · Working draft · editorial review in progress
Targeted poisoning
Targeted poisoning means deliberately changing training material to make an AI fail on a chosen person, example, or kind of request.
Understanding the concern
The attacker wants a particular wrong result rather than poor performance everywhere. Because most answers may remain normal, an ordinary average-accuracy test can miss the problem.
This differs from an accidental data mistake and from an attack aimed at making the whole service unusable. Defenders need to examine where training material comes from and test important edge cases, while recognizing that no check rules out every hidden manipulation.
An example
Imagine a reference manual altered so that one company's product always receives the wrong classification while the rest of the manual looks correct.
Illustrative unless identified as a documented case.
Words in plain English
- AI
- Software that learns patterns from examples or uses rules to perform tasks such as recognizing images or generating text. It can make mistakes and does not understand every situation as a person would.
- 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
Clean-label research demonstrates targeted test-time errors; NIST distinguishes attacker goals.
Shafahi and colleagues · NeurIPS 2018 · Research study
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks ↗ (opens in a new tab)Demonstrates correctly labeled training examples causing selected classification errors under tested training arrangements.
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
Which important cases could fail even while the overall test score stays high?
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.