Attack Anything: Blind DNNs via Universal Background Adversarial Attack

J Lian, S Mei, X Wang, Y Wang, L Wang, Y Lu… - arXiv preprint arXiv …, 2024 - arxiv.org
It has been widely substantiated that deep neural networks (DNNs) are susceptible and
vulnerable to adversarial perturbations. Existing studies mainly focus on performing attacks …

KPIRoot: Efficient Monitoring Metric-based Root Cause Localization in Large-scale Cloud Systems

W Gu, X Sun, J Liu, Y Huo, Z Chen… - 2024 IEEE 35th …, 2024 - ieeexplore.ieee.org
To ensure the reliability of cloud systems, their run-time status reflecting the service quality is
periodically monitored with monitoring metrics, ie, KPIs (key performance indicators). When …

[PDF][PDF] TPAM: Transferable Perceptual-constrained Adversarial Meshes

T Kang, Y Li, J Zhou, S Xin, J Dong, C Tu - 2024 - diglib.eg.org
Triangle meshes are widely used in 3D data representation due to their efficacy in capturing
complex surfaces. Mesh classification, crucial in various applications, has typically been …