Saved in:
Bibliographic Details
Main Authors: Ciosek, Kamil, Petrov, Aleksandr V., Felicioni, Nicolò, Palla, Konstantina
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.14868
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even "fast" attacks such as FGSM remain throughput-limited by the cost of a backward pass. We introduce a family of attacks that eliminates the backward pass by predicting the input gradient from forward-pass hidden states via a lightweight linear regression. The approach is motivated by a kernel view of neural networks and is exact in the Neural Tangent Kernel regime, while remaining effective for practical finite-width models. Empirically, our methods recover much of FGSM's attack performance while using only a small fraction of the time, corresponding to a $532\%$ increase in throughput. These results suggest gradient prediction as a simple and general route to significantly faster adversarial generation under realistic wall-clock constraints.