[HTML][HTML] Security in defect detection: A new one-pixel attack for fooling DNNs

P Wang, Q Li, D Li, S Meng, M Bilal… - Journal of King Saud …, 2023 - Elsevier
Abstract The Industrial 5.0 Model integrates enabling technologies such as deep learning,
digital twins, and the meta-universe with new development concepts. However, model and …

Exposing the Limits of Deepfake Detection using novel Facial mole attack: A Perceptual Black-Box Adversarial Attack Study

QU Ain, A Javed, KM Malik… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Recently, we have observed an exponential growth in highly realistic deepfake videos,
which are often used to spread disinformation, defame individuals, and even influence …

[PDF][PDF] Explanation-based Adversarial Detection with Noise Reduction

J Su, Z Yang, Z Ren, F Jin - practical-dl.github.io
Abstract Deep Neural Networks (DNNs) have achieved tremendous success in various
tasks. However, DNNs expose uncertainty and unreliability against well-designed …

Differential Evolution を用いたAdversarial Examples の生成における複数解探索

串田淳一 - 進化計算学会論文誌, 2023 - jstage.jst.go.jp
抄録 Over the past few years, deep neural networks (DNNs) have shown outstanding
performance in a wide range of domains. However, DNNs have been found to be vulnerable …