Datasets

Adversaries may publish poisoned datasets intended for training or fine-tuning AI models. The dataset may be newly created or a modified variant of a legitimate dataset and may contain manipulated samples, labels, annotations, or metadata.

Adversaries may distribute poisoned datasets through dataset repositories, code repositories, file-sharing services, or compromised data sources. A victim that incorporates the dataset into a training pipeline may be affected by Training Data Poisoning, potentially through AI Supply Chain Compromise.