Concern 31 · Working draft · editorial review in progress
Data poisoning via web scraping
Web-scraping poisoning happens when attackers alter online material that they expect an AI developer to collect for training.
Understanding the concern
Training datasets may point to pages or files whose contents can change. Researchers have shown that material seen by a dataset creator can differ from material downloaded later, creating an opportunity for manipulation.
This is a data-supply problem, not proof that everything on the open web is poisoned. Teams should record what they actually downloaded and review source changes. A trusted-looking list of links does not guarantee that the contents remain trustworthy.
An example
A teacher approves a reading list, but a document at one of the links is replaced before the students download it.
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
The study demonstrates poisoning opportunities in web-scale dataset collection and mutable content.
Carlini and colleagues · Security research
Poisoning Web-Scale Training Datasets is Practical ↗ (opens in a new tab)Studies mutable web sources and collection-time attacks. Demonstrated opportunities are not evidence that every dataset was actually attacked.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Can we show that the material used in training is the material that was originally reviewed?
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.