← Back to all news
arXiv Machine Learning By Lovisa Eriksson, Dave Zachariah, Andr\'e M. H. Teixeira

Adversarial Training of Linear Models under Stealthy Attacks

Read the original on arXiv Machine Learning →

The paper introduces a detector‑based switched model to defend linear predictive models against stealthy false data injection attacks. It derives a convex formulation of the adversarial risk that incorporates protected features and a hyperparameter for attack probability, allowing an explicit trade‑off between clean and attacked data performance. Numerical experiments on real and synthetic datasets demonstrate improved performance on partially attacked data, even when the attack probability is misspecified.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 9

Fast Adversarial Attacks with Gradient Prediction

The paper introduces a new class of adversarial attacks that eliminate the need for a backward pass by predicting input gradients from forward-pass hidden states using lightweight linear regression. The authors theoretically derive exact affine conditional gradient means, proving optimality in the idealized NTK regime, and empirically demonstrate that their methods recover most of FGSM’s performance while achieving a 532% increase in throughput on practical finite-width models. This approach offers a simple and general way to generate adversarial examples much faster under realistic wall‑clock constraints.

By Kamil Ciosek, Aleksandr V. Petrov, Nicol\`o Felicioni, Konstantina Palla
efficiencysafety
More like this →