Adversarial examples have been found for various deep as well as shallow
learning models, and have at various times been suggested to be either fixable
model-specific bugs, or else inherent dataset feature, or both. We present
theoretical and empirical results to show that adversarial examples are
approximate discontinuities resulting from models that specify approximately
bijective maps $f: \Bbb R^n \to \Bbb R^m; n \neq m$ over their inputs, and this
discontinuity follows from the topological invariance of dimension.

本文通过理论和实验证据表明，对于指定的输入，规定近似双射映射 $f：R^n →R^m（n≠m）$ 模型的产生了近似不连续的对抗性例子，并且这种不连续性是维数的拓扑不变性导致的。

维度不变性带来的对抗样本

Adversarial Examples from Dimensional Invariance

Artificial Intelligence techniques have evolved rapidly in recent years,
revolutionising the approaches used to fight against cybercriminals. But as the
cyber security field has progressed, so has malware development, making it an
economic imperative to strengthen businesses' defensive capability against
malware attacks. This review aims to outline the state-of-the-art AI techniques
used in malware detection and prevention, providing an in-depth analysis of the
latest studies in this field. The algorithms investigated consist of Shallow
Learning, Deep Learning and Bio-Inspired Computing, applied to a variety of
platforms, such as PC, cloud, Android and IoT. This survey also touches on the
rapid adoption of AI by cybercriminals as a means to create ever more advanced
malware and exploit the AI algorithms designed to defend against them.

这项综述介绍了最新的人工智能技术在恶意软件检测和预防领域的应用，包括浅层学习、深度学习和生物启发计算，以及 PC、云、Android 和物联网等多种平台。同时，还涉及了黑客采用人工智能设计更高级的恶意软件以及利用人工智能算法自卫的现状。

基于人工智能的恶意软件检测技术现状综述

The State-of-the-Art in AI-Based Malware Detection Techniques: A Review

Recently, the example-based single image spectral reconstruction from RGB
images task, aka, spectral super-resolution was approached by means of deep
learning by Galliani et al. The proposed very deep convolutional neural network
(CNN) achieved superior performance on recent large benchmarks. However,
Aeschbacher et al showed that comparable performance can be achieved by shallow
learning method based on A+, a method introduced for image super-resolution by
Timofte et al. In this paper, we propose a moderately deep CNN model and
substantially improve the reported performance on three spectral reconstruction
standard benchmarks: ICVL, CAVE, and NUS.

本研究提出了一个中等深度的卷积神经网络模型，实验结果在 ICVL、CAVE、NUS 三个光谱重建标准基准上表现出了明显的改进，表明该模型在光谱超分辨率方面有广泛应用前景。

从 RGB 图像中重建光谱的高效卷积神经网络

An efficient CNN for spectral reconstruction from RGB images

The paper characterizes classes of functions for which deep learning can be
exponentially better than shallow learning. Deep convolutional networks are a
special case of these conditions, though weight sharing is not the main reason
for their exponential advantage.

本文探讨了深度学习相对于浅层学习的指数优势，发现深度卷积网络是实现该优势的特例，但是权重共享并不是其主要原因。