arXiv:2608. 13296v1 Announce Type: cross Abstract: Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s.
By Wojciech Zarzecki, Jaros{\l}aw Arabas
The paper investigates Consensus-based Optimization (CBO) as a gradient‑free method for closed‑box adversarial attacks, where imperceptible perturbations fool a classifier without gradient access. It establishes a theoretical link between CBO’s consensus hopping and natural evolution strategies (NES), and relates both to gradient‑based optimization. Experiments demonstrate that CBO can outperform NES and other evolutionary strategies in some scenarios.
By Tim Roith, Leon Bungert, Philipp Wacker
arXiv:2607. 14921v1 Announce Type: cross Abstract: Machine learning models are increasingly adapted in various domains.
By Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh
arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.
By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud
arXiv:2608. 11815v1 Announce Type: new Abstract: Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models.
By Yaohua Liu, Yifan Guo, Jiaxin Gao
arXiv:2511. 12265v2 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) remain vulnerable to diverse adversarial perturbations, motivating multi-attack adversarial training (AT) for improved robustness.
By Rui Wang, Zeming Wei, Xiyue Zhang, Meng Sun