检索结果-内蒙古大学图书馆

作者：邓有强华中科技大学

学位级别：硕士

代码混淆技术是一种对计算机程序代码进行功能上等价转换,但是使代码变得难以阅读和理解的技术。由于软件逆向工程的发展,人们可以对已有的程序软件进行逆向分析,通过反汇编、反编译和动态跟踪等方法分析出程序实现的原理。如果黑客通... 详细信息

代码混淆技术是一种对计算机程序代码进行功能上等价转换,但是使代码变得难以阅读和理解的技术。由于软件逆向工程的发展,人们可以对已有的程序软件进行逆向分析,通过反汇编、反编译和动态跟踪等方法分析出程序实现的原理。如果黑客通过软件逆向分析出程序的关键代码,可能会针对代码存在的漏洞进行攻击。因此,为保证代码安全以及防止代码盗用,就需要对代码进行混淆。然而,传统的代码混淆技术或者是将代码中的元素进行替换,如将函数名、变量名等替换为无意义的名字;或者是在代码中插入一些不影响程序执行的无关代码;或者是将代码中的逻辑替换为功能上等价但更难理解的形式。逆向分析者可以通过具体混淆规则分析出代码的含义,从而实施攻击。本文通过对代码混淆原理的分析及深度学习模型与算法的研究,提出了基于生成式对抗网络的代码混淆模型COMBGAN。首先,设计了能够学习代码逻辑结构的encoder-decoder模型,整合为COMBGAN模型的生成模型。然后,由于常规的encoder-decoder模型只能学习序列的上下文语意,对于代码的控制流信息是无法学习到的,因此将代码处理为抽象语法树路径集合的形式,由抽象语法树的所有路径集合表示代码段。encoder将代码段的所有抽象语法树路径编码为中间向量表示,再由decoder解码为目标代码。最后,构造判别模型以判别生成的目标混淆代码是来自生成模型还是传统混淆器,并对代码进行混淆检查。同时,判别模型与生成模型进行对抗训练,以提高生成模型生成混淆代码的准确率。实验使用了发表于ICLR2019会议上的论文code2seq中的Java-small数据集,并加入混淆代码整合为Java-obscure数据集。在Java-obscure数据集上,COMBGAN模型与现有深度学习模型和代码混淆工具的对比实验显示COMBGAN模型的各项指标均优于其他模型。同时,COMBGAN模型与code2seq模型在Java-small数据集上的实验表明,COMBGAN模型在精确率、召回率及F1值等性能指标上的结果比code2seq分别提升了2.71%,0.14%,1.11%。

关键词：代码混淆软件逆向深度学习 encoder-decoder 生成式对抗网络

来源：评论

学校读者我要写书评

暂无评论

基于深度学习的瓦斯浓度预测方法研究

基于深度学习的瓦斯浓度预测方法研究

引用

作者：徐宁可安徽理工大学

学位级别：硕士

瓦斯事故是影响煤矿井下安全工作的主要原因,对瓦斯浓度进行实时精确的监测是防治瓦斯事件的主要措施。但是,常规的瓦斯浓度预测方法存在很大的局限性。因此,建立精确、高效、实时的瓦斯浓度预测方法,对加强国家煤矿产能,改善行业管理水... 详细信息

瓦斯事故是影响煤矿井下安全工作的主要原因,对瓦斯浓度进行实时精确的监测是防治瓦斯事件的主要措施。但是,常规的瓦斯浓度预测方法存在很大的局限性。因此,建立精确、高效、实时的瓦斯浓度预测方法,对加强国家煤矿产能,改善行业管理水平,提高企业经济效益,保护职工生命安全都具有重要的理论价值与现实意义。为了提高瓦斯浓度的预测精度,本文提出了基于深度学习的瓦斯浓度预测方法。大量实验表明本文提出的方法相比于传统的预测算法能够进一步提高模型的整体预测精度。本研究主要做了如下工作:(1)在数据选择方面,本研究首先以瓦斯数据的时空特性为出发点,采用深度学习算法构建瓦斯浓度预测模型。传统的瓦斯浓度预测方法的输入端只考虑到瓦斯浓度序列的时间特性,缺乏了对空间信息的考虑。本文通过将时间序列因子和空间拓扑因子二者相结合,明确输入数据的属性要求,在提高模型预测精度的同时也大大增强了模型的稳定性。(2)在瓦斯浓度预测模型构建方面,本研究通过改进长短期记忆神经网络(LSTM)的门控单元,增强各个门单元之间的相关性,从而提高提取长期序列特征的能力。本文为了避免传统长短期记忆神经网络在有限的存储空间内提取过多的瓦斯浓度和其他监测数据的冗余特征信息,利用改进后的长短期记忆网络进行相关特征提取,并基于此构建encoder-decoder模型对瓦斯浓度进行长期序列预测。并利用改进的蛇优化算法(SO)简化神经网络的调参过程,避免在训练过程中模型出现局部最优解的情况。(3)在残差序列修正方面,本文利用自适应噪声完备集合经验模态分解(CEEMDAN)算法对残差序列进行分解,接着将各本征模函数作为新一轮的输入数据,然后通过改进的变权组合方法将多个本征模函数的预测值组合起来,作为初始预测值的残差修正序列,进一步提高模型的预测精度。为了验证本文提出方法的有效性,本研究采用矿井真实数据集上进行了实验。实验结果表明,本文提出的encoder-decoder框架下的改进长短期记忆神经网络预测模型优于其他对比模型,能够实现长期准确瓦斯浓度预测。图[26]表[4]参[80]

关键词：深度学习 SO encoder-decoder ILSTM 残差修正瓦斯浓度预测

来源：评论

学校读者我要写书评

暂无评论

General and robust voxel feature learning with Transformer for 3D object detection

引用

Journal of Measurement Science and Instrumentation 2022年第1期13卷 51-60页

作者： LI Yang GE Hongwei Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Wuxi 214122 China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi 214122 China

The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object *** by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional *** first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud *** we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the ***,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object *** voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature *** results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.

关键词： 3D object detection self-attention networks voxel feature with Transformer(VFT) point cloud encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

FORWARD ATTENTION IN SEQUENCE-TO-SEQUENCE ACOUSTIC MODELING FOR SPEECH SYNTHESIS

FORWARD ATTENTION IN SEQUENCE-TO-SEQUENCE ACOUSTIC MODELING ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Jing-Xuan Zhang Zhen-Hua Ling Li-Rong Dai National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei P.R.China

ISBN: (纸本)9781538646595

This paper proposes a forward attention method for the sequence-to-sequence acoustic modeling of speech synthesis. This method is motivated by the nature of the monotonic alignment from phone sequences to acoustic sequences. Only the alignment paths that satisfy the monotonic condition are taken into consideration at each decoder timestep. The modified attention probabilities at each timestep are computed recursively using a forward algorithm. A transition agent for forward attention is further proposed, which helps the attention mechanism to make decisions whether to move forward or stay at each decoder timestep. Experimental results show that the proposed forward attention method achieves faster convergence speed and higher stability than the baseline attention method. Besides, the method of forward attention with transition agent can also help improve the naturalness of synthetic speech and control the speed of synthetic speech effectively.

关键词： sequence-to-sequence model encoder-decoder attention speech synthesis Speech synthesis acoustic modeling decoders Telephone Modeling

来源：评论

学校读者我要写书评

暂无评论

Domain Adapted Abstractive Summarization of Dialogue using Transfer Learning 21

Domain Adapted Abstractive Summarization of Dialogue using T...

引用

Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Rohit Sroch Course5 AI Labs Course5 Intelligence Pvt. Ltd. India India

ISBN: (纸本)9781450385053

Recently, the abstractive dialogue summarization task has been gaining a lot of attention from researchers. Also, unlike news articles and documents with well-structured text, dialogue differs in the sense that it often comes from two or more interlocutors, exchanging information with each other and having an inherent hierarchical structure based on the sequence of utterances by different speakers. This paper proposes a simple but effective hybrid approach that consists of two modules and uses transfer learning by leveraging pretrained language models (PLMs) to generate an abstractive summary. The first module highlights important utterances, capturing the utterance level relationship by adapting an auto-encoding model like BERT based on the unsupervised or supervised method. And then, the second module generates a concise abstractive summary by adapting encoder-decoder models like T5, BART, and PEGASUS. Experiment results on benchmark datasets show that our approach achieves a state-of-the-art performance by adapting to dialogue scenarios and can also be helpful in low-resource settings for domain adaptation.

关键词： PLMs abstractive summary T5 PEGASUS encoder-decoder BERT dialogue summarization BART

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Hierarchy Feature Fusion Generative Adversarial Network for Low-Dose CT Denoising 20

Multi-scale Hierarchy Feature Fusion Generative Adversarial ...

引用

Proceedings of the 2020 9th International Conference on Bioinformatics and Biomedical Science

作者： Ying Bai Haifeng Zhao Shaojie Zhang Dong Nie Zhenyu Tang School of Computer Science and Technology Anhui University Department of Computer Science University of North Carolina at Chapel Hill Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

ISBN: (纸本)9781450388658

Image noise is an inherent issue in low-dose CT (LDCT). Increasing radiation dose can alleviate this problem to some extent, but it also brings potential risks to the patients. Thus, LDCT denoising has raised increasing attention from researchers. Currently, many deep learning based LDCT denoising methods have been proposed with success, such as encoder-decoder. In this paper, we propose a novel multi-scale hierarchy feature fusion based encoder-decoder network within the GAN framework for LDCT denoising. Specifically, a four-stage multi-scale dilated blocks is introduced to integrate low-level features with high-level features. Comparing with the conventional skip connection, which ignores the semantic gap between low-level features and high-level features, the advantage of our method is the effective use of low-level information. In addition, residual learning is also adopted to boost the training of the network. Experimental results on public dataset have demonstrated the superiority of our method over the state-of-the-art methods under comparison in both visual quality and quantitative evaluation.

关键词： Image denoising Low-dose CT encoder-decoder Deep learning Wasserstein GAN

来源：评论

学校读者我要写书评

暂无评论

DLIFT: A deep-learning-based intelligent fund transaction system for financial Internet of Things

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2021年第22期33卷 e5982-e5982页

作者： Hu, Gang Xiang, Zhuoyuan Zhang, Yin Hossain, M. Shamim Zhongnan Univ Econ & Law Sch Informat & Safety Engn Wuhan Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu Peoples R China King Saud Univ Comp Informat Sci Riyadh Saudi Arabia

Analyzing the correlation between two funds can help investors control investment risks and optimize investment portfolios, which has a strong guiding significance for fund investment in reality. Constructing an intelligent investment system with fund correlation analysis capabilities can help investors automatically make profits from financial markets. In previous research, many researchers have built intelligent investment systems using Bayesian networks, support vector machines (SVM), and LSTM models. However, the strong historical dependence between fund data and the high-dimensional and high-noise characteristics of fund data prevent traditional methods from obtaining excellent performance in fund analysis. This paper designs a deep learning-based fund intelligent trading system-DLIFT which has functions such as investment push, income prediction, and risk control. The systems data analysis module is implemented using the Improved RNN model. This model employed encoder-decoder architecture. The encoder is responsible for analyzing the fund's feature, and the decoder is responsible for analyzing the dependency relationship between the historical correlation and the current correlation. LSTM and an attention mechanism are simultaneously applied to the encoder and decoder, which enabled the discovery of the implicit dependence of time series data. This article places the designed system on a historical dataset containing multiple public funds for verification. In specific experiments, the experimental results of the comparative experiments show the superiority of our model. At the same time, the results of the ablation experiment results show that LSTM and attention mechanism play critical role in the proposed system.

关键词： attention mechanism deep learning encoder-decoder fund intelligent transaction system

来源：评论

学校读者我要写书评

暂无评论

Research on Image Description Generation Method Based on G-AoANet 22

Research on Image Description Generation Method Based on G-A...

引用

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

作者： Pingan Qiao Ruixue Shen Yuan Li Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9781450396899

Most of the image description generation methods in the attention-based encoder-decoder framework extract local features from images. Despite the relatively high semantic level of local features, it still has two problems to be solved, one is object loss, where some important objects may be lost when generating image descriptions, and the other is prediction error, as an object may be identified in the wrong class. In this paper, a G-AoANet model is proposed to solve the above problems. The model uses an attention mechanism to combine global features with local features. In this way, our model can selectively focus on both object and contextual information, improving the quality of the generated descriptions. Experimental results show that the model improves the initially reported best CIDEr-D and SPICE scores on the MS COCO dataset by 9.3% and 5.1% respectively.

关键词： encoder-decoder Global attention Image description

来源：评论

学校读者我要写书评

暂无评论

Aerial Image Semantic Segmentation Using Spatial and Channel Attention

Aerial Image Semantic Segmentation Using Spatial and Channel...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Zhu Lan Qingqing Huang Fen Chen Yu Meng School of Resources and Environment University of Electronic Science and Technology of China Chengdu China Aerospace Information Research Institute Chinese Academy of Science Beijing China

ISBN: (纸本)9781728123264

With the development of sensor, remote sensing has become an effective way to observe the Earth. Land cover classification is an important application of remote sensing data. Deep convolutional neural networks (DCNN) have good capability to extract effective image feature. In this paper, an automatic land cover classification method using spatial and channel attention was proposed. encoder-decoder structure was adopted as the network architecture. We used "channel attention" to enhance the function of effective channels. By using "spatial attention" to combining high-level semantic features with low-level features, better land objects boundaries were obtained. The proposed method was tested on ISPRS Potsdam 2D-Semantic Segmentation Challenge Dataset. The results showed that our proposed method, which uses spatial and channel attention with atrous spatial pyramid attention networks (SA-ASPA) outperforms the Deeplab_v3+ in terms of mean Intersection over Union (mIoU) for 5%.

关键词： Semantic segmentation Deep convolution neural networks encoder-decoder Channel attention Spatial attention NETWORK STRUCTURE image feature aerial images Semantics LOW LEVEL Space Autoland

来源：评论

学校读者我要写书评

暂无评论

Low-dose CT image denoising method based on generative adversarial network

引用

Journal of Measurement Science and Instrumentation 2024年第4期15卷 490-498页

作者： JIAO Fengyuan YANG Zhixiu SHI Shaojie CAO Weiguo Shanxi Provincial Key Laboratory for Biomedical Imaging and Big Data North University of ChinaTaiyuan 030051China School of Information and Communication Engineering North University of ChinaTaiyuan 030051China School of Environment and Safety Engineering North University of ChinaTaiyuan 030051China

In order to solve the problems of artifacts and noise in low-dose computed tomography(CT)images in clinical medical diagnosis,an improved image denoising algorithm under the architecture of generative adversarial network(GAN)was ***,a noise model based on style GAN2 was constructed to estimate the real noise distribution,and the noise information similar to the real noise distribution was generated as the experimental noise data ***,a network model with encoder-decoder architecture as the core based on GAN idea was constructed,and the network model was trained with the generated noise data set until it reached the optimal ***,the noise and artifacts in low-dose CT images could be removed by inputting low-dose CT images into the denoising *** experimental results showed that the constructed network model based on GAN architecture improved the utilization rate of noise feature information and the stability of network training,removed image noise and artifacts,and reconstructed image with rich texture and realistic visual effect.

关键词： low-dose CT image generative adversarial network noise and artifacts encoder-decoder atrous spatial pyramid pooling(ASPP)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：