Fast Adversarial Attacks with Gradient Prediction

Name: Fast Adversarial Attacks with Gradient Prediction
Uploaded: 2026-10-17T22:21:35.658279+00:00
Duration: 299 s
Description: The authors introduced an attack method that eliminates the computationally expensive backward pass by predicting input gradients from forward-pass hidden states using a simple linear regression. This technique recovers much of Fast Gradient Sign Method (FGSM) performance while increasing throughput by 532%, making adversarial example generation significantly faster for practical applications.

The authors introduced an attack method that eliminates the computationally expensive backward pass by predicting input gradients from forward-pass hidden states using a simple linear regression. This technique recovers much of Fast Gradient Sign Method (FGSM) performance while increasing throughput by 532%, making adversarial example generation significantly faster for practical applications.

Open the full episode