Unreliable source attribution risk for AI
Description
Source attribution is the AI system's ability to describe from what training data it generated a portion or all its output. Since current techniques are based on approximations, attributions might be incorrect.
Why is unreliable source attribution a concern for foundation models?
Low-quality attributions make it difficult for users, model validators, and auditors to understand and trust the model. The use of synthetic data can complicate source attribution, as the model may be unable to identify synthetic data or accurately identify the original source of the synthetic data, potentially leading to incorrect or misleading attributions.
Parent topic: AI risk atlas
We provide examples covered by the press to help explain many of the foundation models' risks. Many of these events covered by the press are either still evolving or have been resolved, and referencing them can help the reader understand the potential risks and work toward mitigations. Highlighting these examples are for illustrative purposes only.