Data poisoning refers to a method of attack in which an adversary deliberately introduces misleading or harmful data into a apprentissage automatique (ML) training dataset. The objective of this malicious act is to compromise the integrity of the ML model, leading to incorrect predictions or classifications when the model is deployed in real-world applications.
Dans de nombreux apprentissages automatiques systems, the quality and reliability of the données d'entraînement are crucial for the model’s performance. When an attacker successfully implements data poisoning, they can manipulate the learning process by injecting biased or false information. This can result in a model that performs poorly, behaves unpredictably, or even serves the attacker’s goals by making specific predictions that benefit them.
La poisoning de données peut prendre diverses formes, notamment :
- Flip de labels : Changer les étiquettes de certains points de données pour induire en erreur le modèle lors de l'entraînement.
- Attaques par porte dérobée : Inserting specific data patterns that cause the model to behave incorrectly only when those patterns are present.
- Ajout de valeurs aberrantes : Introducing extreme or unusual data points that skew the model’s understanding of the normal distribution des données.
Atténuer l'empoisonnement des données implique plusieurs stratégies, telles que des méthodes robustes validation des données techniques, la détection d'anomalies, and using diverse training datasets to minimize the impact of any single source of data corruption. Continuous monitoring and updating of models can also help to reduce the risk of data poisoning attacks.