arXiv:2606. 27832v1 Announce Type: new Abstract: Statistical adversarial detection (SAD) treats detection as a two-sample test.
arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.
arXiv:2606. 28416v1 Announce Type: cross Abstract: Deep neural networks (DNNs) have shown outstanding performance in visual recognition tasks within vision sensor networks; however, they are still vulnerable to adversarial manipulations and imperceptible perturbations that can lead to erroneous predictions.
arXiv:2606. 01437v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) are highly susceptible to adversarial perturbations, leading to extensive research on robustness for safety-critical applications.
arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.
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.
arXiv:2607. 16348v1 Announce Type: cross Abstract: Machine learning-based intrusion detection systems (IDSs) often suffer from class imbalance and vulnerability to adversarial attacks, leading to degraded detection performance and reduced robustness.
arXiv:2606. 31653v1 Announce Type: cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on the worst-case loss over an allowed perturbation set.
arXiv:2607. 22722v1 Announce Type: cross Abstract: Almost all adversarial attacks add an imperceptible perturbation to fool a model.
arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.
arXiv:2512. 12997v2 Announce Type: replace-cross Abstract: CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks.
arXiv:2607. 17336v1 Announce Type: new Abstract: Drift detection is a core component of production machine learning monitoring systems, where detectors are used to compare incoming data with a reference distribution and trigger alerts when changes occur.
The paper introduces Inverse Knowledge Distillation (IKD), an attack‑agnostic technique that enhances adversarial transferability by maximizing the discrepancy between benign and adversarial prediction distributions on a surrogate model. IKD employs a CE/KL‑equivalent soft‑label objective to push adversarial predictions away from a fixed benign anchor, leveraging Fisher‑sensitive surrogate directions. The authors provide theoretical analysis showing CE and KL induce identical gradients, derive a lower bound on Fisher‑subspace overlap, and demonstrate through extensive ImageNet experiments that IKD consistently improves black‑box attack performance across CNN, ViT, and defended models.