Concern 39 · Working draft · editorial review in progress
Federated-learning poisoning
Federated-learning poisoning occurs when a participant sends a harmful update into a model trained across several separate devices or organizations.
Understanding the concern
Federated learning can keep raw records in their original location while combining learned updates. That reduces some data movement, but it does not mean every participant's contribution is trustworthy.
Research has shown backdoor behavior introduced through malicious updates under particular assumptions. Privacy and security are separate questions: hiding raw data does not automatically stop someone from influencing the shared model. Teams need a clear account of which participants and updates they trust.
An example
A shared recipe can be spoiled by one contributor's amendment even if nobody shares their whole kitchen notebook.
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.
- Federated learning
- Training across several devices or organizations while keeping some data in its original location. It does not automatically remove all privacy risks.
Evidence and its limits
The study demonstrates model-replacement attacks in a federated setting; it does not show that all federated systems are equally vulnerable.
Bagdasaryan and colleagues · Research study
How To Backdoor Federated Learning ↗ (opens in a new tab)Demonstrates malicious model updates and backdoor behavior under federated-learning attack assumptions.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
How are harmful contributions detected when individual training records remain private?
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.