arXiv:2607. 04145v1 Announce Type: new Abstract: Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models.
By Naman Goyal, Milan Chaudhari
We’ve developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during training. Our method yields a new metric, UAR (Unforeseen Attack Robustness), which evaluates the robustness of a single model against an unanticipated attack, and highlights the need to measure performance across a more diverse range of unforeseen attacks.
The paper introduces Phase Attacks, a novel adversarial technique that targets the phase component of complex-valued inputs in complex-valued neural networks (CVNNs). It also extends traditional adversarial attacks to the complex domain and compares CVNNs with real-valued neural networks (RVNNs). The results show that CVNNs can be more robust in some cases, yet both architectures are highly vulnerable to phase perturbations, with Phase Attacks causing greater performance degradation than equivalent magnitude‑based attacks.
By Florian Eilers, Christof Duhme, Xiaoyi Jiang
arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.
By Nicolas Stalder, Benjamin F. Grewe, Matteo Saponati, Pau Vilimelis Aceituno
arXiv:2506.12454v2 Announce Type: replace-cross
Abstract: What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this wor...
By Matteo Vilucchio, Lenka Zdeborov\'a, Bruno Loureiro
arXiv:2608.21488v1 Announce Type: cross
Abstract: While machine learning models have demonstrated strong performance in many domains, these models have shown profound vulnerabilities when they are ex...
By Mohammad Meymani, Roozbeh Razavi-Far