Evasion Attacks: How Adversarial Noise Bypasses ML Classifiers
This paper presents a reproducible, educational study of evasion attacks in image classification and text classification. A compact convolutional network trained on MNIST reached 98.63% clean test accuracy and was evaluated under two white-box attacks. Under FGSM, accuracy fell to 60.20% at $\epsilon$ = 0.15 and 1.72%...
Parker Hummel, Ryne Skabo, Muhammad Abusaqer
· 0 citations