How to train your model dynamically using adversarial data

Attacking machine learning with adversarial examples

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this post we’ll show how adversarial examples work across different mediums, and will discuss why securing systems against them can be difficult.

Adversarial Training of Linear Models under Stealthy Attacks

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.

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave like backdoor-like triggers without being maliciously inserted.

Transfer of adversarial robustness between perturbation types

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.

Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey

arXiv:2403. 00420v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments.