Definition
This adversarial technique aims to compromise the integrity of machine learning models by altering the training data. By introducing subtle errors or biased examples, attackers can cause the model to make incorrect predictions on specific inputs or generally reduce its accuracy. It poses a significant risk in open-data environments or federated learning systems where data sources are not fully trusted.
Summary
Data poisoning is a security attack where malicious actors inject corrupted or misleading data into a training set to degrade model performance.
Key Concepts
- Adversarial Attack
- Model Integrity
- Training Data Security
- Backdoor Attacks
Use Cases
- Security testing of ML pipelines
- Understanding vulnerabilities in open datasets
- Developing robust defense mechanisms