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.
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.
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.
arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.
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.
arXiv:2608. 12535v1 Announce Type: new Abstract: Deep learning models are widely used for time series analysis in domains such as healthcare, finance, energy systems, and environmental monitoring.
The paper demonstrates that image knowledge distillation can be backdoored even when the teacher model is clean, by poisoning the distillation dataset with triggered and manipulated images that the teacher already classifies as a target label. The attack, effective at poisoning rates as low as 10%, uses targeted adversarial perturbations and GAN-based class transitions to embed a backdoor into the student model while preserving its performance on clean data. The study highlights that the security of knowledge distillation depends not only on the teacher but also on the integrity of the distillation data.
arXiv:2510. 09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge.
The paper investigates how adversarial examples transfer between client models in federated learning and explores the relationship between these examples and client data distributions. It proposes a defense strategy based on adversarial training that leverages the transferability of model robustness. Experiments on real-life datasets demonstrate that the new attack and defense methods outperform existing state‑of‑the‑art approaches.
arXiv:2608.29510v1 Announce Type: cross Abstract: Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches...
The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of machine learning models. However, the involvement of a...