arXiv:2508. 19445v3 Announce Type: replace Abstract: Given a trained neural network, can any specified output be generated by some input?
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.
arXiv:2411. 10023v3 Announce Type: replace Abstract: Deep neural networks have enabled numerous studies and applications on both Euclidean data, such as images and text, and non-Euclidean data, such as graphs.
arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.
arXiv:2406. 10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization.
arXiv:2510. 11709v2 Announce Type: replace-cross Abstract: Why do adversarial examples exist, and why do they transfer between models?
arXiv:2605.13214v3 Announce Type: replace-cross Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a cl...
The paper introduces a new framework for creating frequency‑based adversarial attacks that are grounded in an explicit optimization problem. By defining a perturbation constraint set linked to structured, non‑orthogonal transforms, the authors show that attacks can be generated as weighted σ‒projections onto this set, providing a clear geometric characterization. Experiments on standard datasets demonstrate that these attacks are highly effective across both pretrained and robust models, even on unseen architectures.