Concern 169 · Working draft · editorial review in progress
Compromised training pipelines
A compromised training pipeline lets an attacker alter the process that turns data and code into a model.
Understanding the concern
The pipeline includes data preparation, training software, stored settings, and release steps. An unauthorized change can enter before the final files exist. Even a clean starting dataset cannot protect a model if later parts of the process are tampered with.
This differs from poisoning only the training examples. The attacker may change code, replace a saved model, or interfere with a build dependency. Teams need a traceable record of what ran and which artifacts it produced, along with limits on who can change each step.
An example
A food factory checks its ingredients but someone changes the recipe controls or swaps the finished packages.
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 AI development profile addresses lifecycle integrity and provenance; the factory analogy is illustrative.
NIST · SP 800-218A · 2024 · Official guidance
Secure Software Development Practices for Generative AI and Dual-Use Foundation Models ↗ (opens in a new tab)Adds AI-specific lifecycle practices to secure software development; guidance does not certify a particular system.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Can we trace a released model back to the authorized data, code, settings, and build process?
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.
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?
Prudence
Prudence means using careful judgment before and during action. It balances worthwhile opportunities with the need to avoid harm that could have been anticipated.
Start with a limited trial, set stopping points, and prefer choices that can be undone when uncertainty is high. Review what happens rather than assuming the original plan remains sound.
Ask together: What is a careful next step, and when should we stop or change course?
Accountability
Accountability means being answerable for decisions and taking responsibility for repair. It requires more than saying that the software made the choice.
Name the person or team responsible, keep useful records, and give them authority to correct problems. Make the route to a complaint clear to the people affected.
Ask together: Who will answer for the outcome and help put things right?
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.