SOURCE-LINKED INTELLIGENCE

Empirical Evaluation of Data Poisoning Attacks in Supervised Learning

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Data poisoning corrupts training data to degrade a model or to plant attacker-controlled behavior. This study evaluates two representative training-time attacks, label flipping and backdoor poisoning, on MNIST and Fashion-MNIST with three baseline classifiers: Logistic Regression, Linear SVM, and Random Forest. Clean training is compared with poisoning rates of 5%, 10%, and 20% using clean-test accuracy, macro-precision, macro-recall, macro-F1, and, for backdoors, attack success rate. Label flipping caused clear degradation, largest for Logistic Regression and Linear SVM, while Random Forest s

Read original source ↗ Open in workspace

recordType

paper

region

Global