Machine fault diagnosis with small sample based on variational information constrained generative adversarial network

In actual engineering scenarios, limited fault data leads to insufficient model training and over-fitting, which negatively affects the diagnostic performance of intelligent diagnostic models. To solve the problem, this paper proposes a variational information constrained generative adversarial network (VICGAN) for effective machine fault diagnosis. Firstly, by incorporating the encoder into the discriminator to map the deep features, an improved generative adversarial network with stronger data synthesis capability is established. Secondly, to promote the stable training of the model and guarantee better convergence, a variational information constraint technique is utilized, which constrains the input signals and deep features of the discriminator using the information bottleneck method. In addition, a representation matching module is added to impose restrictions on the generator, avoiding the mode collapse problem and boosting the sample diversity. Two rolling bearing datasets are utilized to verify the effectiveness and stability of the presented network, which demonstrates that the presented network has an admirable ability in processing fault diagnosis with few samples, and performs better than state-of-the-art approaches.     

DEFIDNET: A framework for optimal allocation of cyberdefenses in Intrusion Detection Networks

Intrusion Detection Networks (IDN) are distributed cyberdefense systems composed of different nodes performing local detection and filtering functions, as well as sharing information with other nodes in the IDN. The security and resilience of such cyberdefense systems are paramount, since an attacker will try to evade them or render them unusable before attacking the end systems. In this paper, we introduce a system model for IDN nodes in terms of their logical components, functions, and communication channels. This allows us to model different IDN node roles (e.g., detectors, filters, aggregators, correlators, etc.) and architectures (e.g., hierarchical, centralized, fully distributed, etc.). We then introduce a threat model that considers adversarial actions executed against particular IDN nodes, and also the propagation of such actions throughout connected nodes. Based on such models, we finally introduce a countermeasure allocation model based on a multi-objective optimization algorithm to obtain optimal allocation strategies that minimize both risk and cost. Our experimental results obtained through simulation with different IDN architectures illustrate the benefit of our framework to design and reconfigure cyberdefense systems optimally.     

Image Super-Resolution Based on Generative Adversarial Networks: A Brief Review

Single image super resolution (SISR) is an important research content in the field of computer vision and image processing. With the rapid development of deep neural networks, different image super-resolution models have emerged. Compared to some traditional SISR methods, deep learning-based methods can complete the superresolution tasks through a single image. In addition, compared with the SISR methods using traditional convolutional neural networks, SISR based on generative adversarial networks (GAN) has achieved the most advanced visual performance. In this review, we first explore the challenges faced by SISR and introduce some common datasets and evaluation metrics. Then, we review the improved network structures and loss functions of GAN-based perceptual SISR. Subsequently, the advantages and disadvantages of different networks are analyzed by multiple comparative experiments. Finally, we summarize the paper and look forward to the future development trends of GAN-based perceptual SISR.     

单片机破解的常用方法及应对策略

介绍了单片机内部密码破解的常用方法，重点说明了侵入型攻击／物理攻击方法的详细步骤，最后，从应用角度出发，提出了对付破解的几点建议。     

Binary rewriting and call interception for efficient runtime protection against buffer overflows

Buffer overflow vulnerabilities are one of the most commonly and widely exploited security vulnerabilities in programs. Most existing solutions for avoiding buffer overflows are either inadequate, inefficient or incompatible with existing code. In this paper, we present a novel approach for transparent and efficient runtime protection against buffer overflows. The approach is implemented by two tools: Type Information Extractor and Depositor (TIED) and LibsafePlus. TIED is first used on a binary executable or shared library file to extract type information from the debugging information inserted in the file by the compiler and reinsert it in the file as a data structure available at runtime. LibsafePlus is a shared library that is preloaded when the program is run. LibsafePlus intercepts unsafe C library calls such as strcpy and uses the type information made available by TIED at runtime to determine whether it would be ‘safe’ to carry out the operation. With our simple design we are able to protect most applications with a performance overhead of less than 10%. Copyright © 2006 John Wiley & Sons, Ltd.     

数字水印攻击及对策分析

数字水印技术作为数字媒体版权保护的重要手段越来越引起人们的重视。文章讨论了数字水印的概念、特征,重点介绍了数字水印的鲁棒性及影响数字水印鲁棒性的因素,总结和分析了数字水印主要攻击方式并提出相应的应对措施。     

基于Transformer实现文本导向的图像编辑

为方便非专业用户修图,提出一种基于Transformer的图像编辑模型TMGAN,使用户可通过自然语言描述自动修改图像属性。TMGAN整体框架采用生成对抗网络,生成器采用Transformer编码器结构提取全局上下文信息,解决生成图像不够真实的问题;判别器包含基于Transformer的多尺度判别器和词级判别器两部分,给生成器细粒度的反馈,生成符合文本描述的目标图像且保留原始图像中与文本描述无关的内容。实验表明,此模型在CUB Bird数据集上,IS（inception score）、FID（Fréchet inception distance）以及MP（manipulation precision）度量指标分别达到了9.07、8.64和0.081。提出的TMGAN模型对比现有模型效果更好,生成图像既满足了给定文本的属性要求又具有高语义性。     

Speech Enhancement via Residual Dense Generative Adversarial Network

Generative adversarial networks (GANs) are paid more attention to dealing with the end-to-end speech enhancement in recent years. Various GAN-based enhancement methods are presented to improve the quality of reconstructed speech. However, the performance of these GAN-based methods is worse than those of masking-based methods. To tackle this problem, we propose speech enhancement method with a residual dense generative adversarial network (RDGAN) contributing to map the log-power spectrum (LPS) of degraded speech to the clean one. In detail, a residual dense block (RDB) architecture is designed to better estimate the LPS of clean speech, which can extract rich local features of LPS through densely connected convolution layers. Meanwhile, sequential RDB connections are incorporated on various scales of LPS. It significantly increases the feature learning flexibility and robustness in the time-frequency domain. Simulations show that the proposed method achieves attractive speech enhancement performance in various acoustic environments. Specifically, in the untrained acoustic test with limited priors, e.g., unmatched signal-to-noise ratio (SNR) and unmatched noise category, RDGAN can still outperform the existing GAN-based methods and masking-based method in the measures of PESQ and other evaluation indexes. It indicates that our method is more generalized in untrained conditions.     

Semisupervised Encrypted Traffic Identification Based on Auxiliary Classification Generative Adversarial Network

The rapidly increasing popularity of mobile devices has changed the methods with which people access various network services and increased network traffic markedly. Over the past few decades, network traffic identification has been a research hotspot in the field of network management and security monitoring. However, as more network services use encryption technology, network traffic identification faces many challenges. Although classic machine learning methods can solve many problems that cannot be solved by port- and payload-based methods, manually extract features that are frequently updated is time-consuming and labor-intensive. Deep learning has good automatic feature learning capabilities and is an ideal method for network traffic identification, particularly encrypted traffic identification; Existing recognition methods based on deep learning primarily use supervised learning methods and rely on many labeled samples. However, in real scenarios, labeled samples are often difficult to obtain. This paper adjusts the structure of the auxiliary classification generation adversarial network (ACGAN) so that it can use unlabeled samples for training, and use the wasserstein distance instead of the original cross entropy as the loss function to achieve semisupervised learning. Experimental results show that the identification accuracy of ISCX and USTC data sets using the proposed method yields markedly better performance when the number of labeled samples is small compared to that of convolutional neural network (CNN) based classifier.