8 citations · 9 across the 2 of their papers we have counts for
3 papers
cs.CV2020★ 1 cited
Search Space of Adversarial Perturbations against Image Filters
Dang Duy Thang, Toshihiro Matsui
The superiority of deep learning performance is threatened by safety issues for itself. Recent findings have shown that deep learning systems are very weak to adversarial examples,…
cs.CV2019
Automated Detection System for Adversarial Examples with High-Frequency Noises Sieve
Dang Duy Thang, Toshihiro Matsui
Deep neural networks are being applied in many tasks with encouraging results, and have often reached human-level performance. However, deep neural networks are vulnerable to well-…
cs.CV2019★ 8 cited
Image Transformation can make Neural Networks more robust against Adversarial Examples
Dang Duy Thang, Toshihiro Matsui
Neural networks are being applied in many tasks related to IoT with encouraging results. For example, neural networks can precisely detect human, objects and animal via surveillanc…