scholarly journals Automated Software Vulnerability Detection Based on Hybrid Neural Network

2021 ◽  
Vol 11 (7) ◽  
pp. 3201
Author(s):  
Xin Li ◽  
Lu Wang ◽  
Yang Xin ◽  
Yixian Yang ◽  
Qifeng Tang ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Detection Methods ◽  
Buffer Size ◽  
Intermediate Representation ◽  
Vulnerability Detection ◽  
Global Features ◽  
Hybrid Neural Network ◽  
Structure Information ◽  
High Level

Vulnerabilities threaten the security of information systems. It is crucial to detect and patch vulnerabilities before attacks happen. However, existing vulnerability detection methods suffer from long-term dependency, out of vocabulary, bias towards global features or local features, and coarse detection granularity. This paper proposes an automatic vulnerability detection framework in source code based on a hybrid neural network. First, the inputs are transformed into an intermediate representation with explicit structure information using lower level virtual machine intermediate representation (LLVM IR) and backward program slicing. After the transformation, the size of samples and the size of vocabulary are significantly reduced. A hybrid neural network model is then applied to extract high-level features of vulnerability, which learns features both from convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The former is applied to learn local vulnerability features, such as buffer size. Furthermore, the latter is utilized to learn global features, such as data dependency. The extracted features are made up of concatenated outputs of CNN and RNN. Experiments are performed to validate our vulnerability detection method. The results show that our proposed method achieves excellent results with F1-scores of 98.6% and accuracy of 99.0% on the SARD dataset. It outperforms state-of-the-art methods.

scholarly journals Automated Vulnerability Detection in Source Code Using Minimum Intermediate Representation Learning

2020 ◽  
Vol 10 (5) ◽  
pp. 1692 ◽  
Author(s):  
Xin Li ◽  
Lu Wang ◽  
Yang Xin ◽  
Yixian Yang ◽  
Yuling Chen
Keyword(s):  
Detection Method ◽  
False Positive Rate ◽  
Source Code ◽  
Representation Learning ◽  
Detection Methods ◽  
Intermediate Representation ◽  
Vulnerability Detection ◽  
Network Intrusion ◽  
Intelligent Methods ◽  
High Level

Vulnerability is one of the root causes of network intrusion. An effective way to mitigate security threats is to discover and patch vulnerabilities before an attack. Traditional vulnerability detection methods rely on manual participation and incur a high false positive rate. The intelligent vulnerability detection methods suffer from the problems of long-term dependence, out of vocabulary, coarse detection granularity and lack of vulnerable samples. This paper proposes an automated and intelligent vulnerability detection method in source code based on the minimum intermediate representation learning. First, the sample in the form of source code is transformed into a minimum intermediate representation to exclude the irrelevant items and reduce the length of the dependency. Next, the intermediate representation is transformed into a real value vector through pre-training on an extended corpus, and the structure and semantic information are retained. Then, the vector is fed to three concatenated convolutional neural networks to obtain high-level features of vulnerability. Last, a classifier is trained using the learned features. To validate this vulnerability detection method, an experiment was performed. The empirical results confirmed that compared with the traditional methods and the state-of-the-art intelligent methods, our method has a better performance with fine granularity.

scholarly journals SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks

2021 ◽  
Vol 40 (3) ◽  
pp. 1-13
Author(s):  
Lumin Yang ◽  
Jiajie Zhuang ◽  
Hongbo Fu ◽  
Xiangzhi Wei ◽  
Kun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Large Scale ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Structure Information ◽  
Graph Neural Networks ◽  
Node Labels ◽  
Point Level

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. We treat an input stroke-based sketch as a graph with nodes representing the sampled points along input strokes and edges encoding the stroke structure information. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture to extract the features at three levels, i.e., point-level, stroke-level, and sketch-level. SketchGNN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.2% in the pixel-based metric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods.

scholarly journals Robust and fast post-processing of single-shot spin qubit detection events with a neural network

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tom Struck ◽  
Javed Lindner ◽  
Arne Hollmann ◽  
Floyd Schauer ◽  
Andreas Schmidbauer ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bayesian Inference ◽  
Rabi Oscillation ◽  
Detection Methods ◽  
Measured Signal ◽  
Single Shot ◽  
Post Processing ◽  
Readout Signal ◽  
Spin Qubit

AbstractEstablishing low-error and fast detection methods for qubit readout is crucial for efficient quantum error correction. Here, we test neural networks to classify a collection of single-shot spin detection events, which are the readout signal of our qubit measurements. This readout signal contains a stochastic peak, for which a Bayesian inference filter including Gaussian noise is theoretically optimal. Hence, we benchmark our neural networks trained by various strategies versus this latter algorithm. Training of the network with 106 experimentally recorded single-shot readout traces does not improve the post-processing performance. A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter. This neural network turns out to be more robust to fluctuations in the signal offset, length and delay as well as in the signal-to-noise ratio. Notably, we find an increase of 7% in the visibility of the Rabi oscillation when we employ a network trained by synthetic readout traces combined with measured signal noise of our setup. Our contribution thus represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.

scholarly journals Real-Time Adversarial Attack Detection with Deep Image Prior Initialized as a High-Level Representation Based Blurring Network

Electronics ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 52
Author(s):  
Richard Evan Sutanto ◽  
Sukho Lee
Keyword(s):  
Neural Network ◽  
Attack Detection ◽  
Detection Methods ◽  
Defense System ◽  
Image Prior ◽  
The Neural Network ◽  
Adversarial Examples ◽  
Deep Image ◽  
Adversarial Attack ◽  
High Level

Several recent studies have shown that artificial intelligence (AI) systems can malfunction due to intentionally manipulated data coming through normal channels. Such kinds of manipulated data are called adversarial examples. Adversarial examples can pose a major threat to an AI-led society when an attacker uses them as means to attack an AI system, which is called an adversarial attack. Therefore, major IT companies such as Google are now studying ways to build AI systems which are robust against adversarial attacks by developing effective defense methods. However, one of the reasons why it is difficult to establish an effective defense system is due to the fact that it is difficult to know in advance what kind of adversarial attack method the opponent is using. Therefore, in this paper, we propose a method to detect the adversarial noise without knowledge of the kind of adversarial noise used by the attacker. For this end, we propose a blurring network that is trained only with normal images and also use it as an initial condition of the Deep Image Prior (DIP) network. This is in contrast to other neural network based detection methods, which require the use of many adversarial noisy images for the training of the neural network. Experimental results indicate the validity of the proposed method.

scholarly journals KeratoDetect: Keratoconus Detection Algorithm Using Convolutional Neural Networks

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Alexandru Lavric ◽  
Popa Valentin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Treatment Options ◽  
Diagnostic Errors ◽  
Detection Algorithm ◽  
Rapid Screening ◽  
Test Set ◽  
Corneal Deformation ◽  
Long Time ◽  
High Level

Keratoconus (KTC) is a noninflammatory disorder characterized by progressive thinning, corneal deformation, and scarring of the cornea. The pathological mechanisms of this condition have been investigated for a long time. In recent years, this disease has come to the attention of many research centers because the number of people diagnosed with keratoconus is on the rise. In this context, solutions that facilitate both the diagnostic and treatment options are quickly needed. The main contribution of this paper is the implementation of an algorithm that is able to determine whether an eye is affected or not by keratoconus. The KeratoDetect algorithm analyzes the corneal topography of the eye using a convolutional neural network (CNN) that is able to extract and learn the features of a keratoconus eye. The results show that the KeratoDetect algorithm ensures a high level of performance, obtaining an accuracy of 99.33% on the data test set. KeratoDetect can assist the ophthalmologist in rapid screening of its patients, thus reducing diagnostic errors and facilitating treatment.

scholarly journals Feature-Based Interpretation of the Deep Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (21) ◽  
pp. 2687
Author(s):  
Eun-Hun Lee ◽  
Hyeoncheol Kim
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Network ◽  
Lower Layer ◽  
Network Models ◽  
Neural Network Models ◽  
Network Pruning ◽  
The Neural Network ◽  
Single Instance ◽  
High Level

The significant advantage of deep neural networks is that the upper layer can capture the high-level features of data based on the information acquired from the lower layer by stacking layers deeply. Since it is challenging to interpret what knowledge the neural network has learned, various studies for explaining neural networks have emerged to overcome this problem. However, these studies generate the local explanation of a single instance rather than providing a generalized global interpretation of the neural network model itself. To overcome such drawbacks of the previous approaches, we propose the global interpretation method for the deep neural network through features of the model. We first analyzed the relationship between the input and hidden layers to represent the high-level features of the model, then interpreted the decision-making process of neural networks through high-level features. In addition, we applied network pruning techniques to make concise explanations and analyzed the effect of layer complexity on interpretability. We present experiments on the proposed approach using three different datasets and show that our approach could generate global explanations on deep neural network models with high accuracy and fidelity.

scholarly journals Hoax Detection System on Twitter using Feed-Forward and Back-Propagation Neural Networks Classification Method

2020 ◽  
Vol 4 (4) ◽  
pp. 655-663
Author(s):  
Crisanadenta Wintang Kencana ◽  
Erwin Budi Setiawan ◽  
Isman Kurniawan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Social Media ◽  
Detection System ◽  
Back Propagation ◽  
Detection Methods ◽  
Network Connection ◽  
The Neural Network ◽  
The World ◽  
False News

Social media is one of the ways to connect every individual in the world. It also used by irresponsible people to spread a hoax. Hoax is false news that is made as if it is true. It may cause anxiety and panic in society. It can affect the social and political conditions. This era, the most popular social media is Twitter. It is a place for sharing information and users around the world can share and receive news in short messages or called tweet. Hoax detection gained significant interest in the last decade. Existing hoax detection methods are based on either news-content or social-context using user-based features. In this study, we present a hoax detection based on FF & BP neural networks. In the developing of it, we used two vectorization methods, TF-IDF and Word2Vec. Our model is designed to automatically learn features for hoax news classification through several hidden layers built into the neural network.  The neural network is actually using the ability of the human brain that is able to provide stimulation, process, and output. It works by the neuron to process every information that enters, then is processed through a network connection, and will continue learning to produce abilities to do classification. Our proposed model would be helpful to provide a better solution for hoax detection. Data collection obtained through crawling used Twitter API and retrieve data according to the keywords and hashtags. The neural networks highest accuracy obtained using TF-IDF by 78.76%. We also found that data quality affects the performance.

scholarly journals Incorporating Context-Relevant Knowledge into Convolutional Neural Networks for Short Text Classification

2019 ◽  
Vol 33 ◽  
pp. 10067-10068 ◽  
Author(s):  
Jingyun Xu ◽  
Yi Cai
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Text Classification ◽  
Classification Methods ◽  
Short Text ◽  
Proposed Model ◽  
High Level ◽  
Context Features

Some text classification methods don’t work well on short texts due to the data sparsity. What’s more, they don’t fully exploit context-relevant knowledge. In order to tackle these problems, we propose a neural network to incorporate context-relevant knowledge into a convolutional neural network for short text classification. Our model consists of two modules. The first module utilizes two layers to extract concept and context features respectively and then employs an attention layer to extract those context-relevant concepts. The second module utilizes a convolutional neural network to extract high-level features from the word and the contextrelevant concept features. The experimental results on three datasets show that our proposed model outperforms the stateof-the-art models.

CrowdTC: Crowd-powered Learning for Text Classification

2021 ◽  
Vol 16 (1) ◽  
pp. 1-23
Author(s):  
Keyu Yang ◽  
Yunjun Gao ◽  
Lei Liang ◽  
Song Bian ◽  
Lu Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Text Classification ◽  
Deep Neural Networks ◽  
Semantic Information ◽  
Human Beings ◽  
Hybrid Neural Network ◽  
Public Datasets ◽  
Almost All ◽  
The Cost

Text classification is a fundamental task in content analysis. Nowadays, deep learning has demonstrated promising performance in text classification compared with shallow models. However, almost all the existing models do not take advantage of the wisdom of human beings to help text classification. Human beings are more intelligent and capable than machine learning models in terms of understanding and capturing the implicit semantic information from text. In this article, we try to take guidance from human beings to classify text. We propose Crowd-powered learning for Text Classification (CrowdTC for short). We design and post the questions on a crowdsourcing platform to extract keywords in text. Sampling and clustering techniques are utilized to reduce the cost of crowdsourcing. Also, we present an attention-based neural network and a hybrid neural network to incorporate the extracted keywords as human guidance into deep neural networks. Extensive experiments on public datasets confirm that CrowdTC improves the text classification accuracy of neural networks by using the crowd-powered keyword guidance.

DEVELOPING TIME-BASED CLUSTERING NEURAL NETWORKS TO USE CHANGE-POINT DETECTION: APPLICATION TO FINANCIAL TIME SERIES

2005 ◽  
Vol 22 (01) ◽  
pp. 51-70 ◽  
Author(s):  
KYONG JOO OH ◽  
TAE HYUP ROH ◽  
MYUNG SANG MOON
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Change Point ◽  
Financial Time Series ◽  
Change Point Detection ◽  
Detection Methods ◽  
Financial Time ◽  
Point Groups ◽  
Point Detection

This study suggests time-based clustering models integrating change-point detection and neural networks, and applies them to financial time series forecasting. The basic concept of the proposed models is to obtain intervals divided by change points, to identify them as change-point groups, and to involve them in the forecasting model. The proposed models consist of two stages. The first stage, the clustering neural network modeling stage, is to detect successive change points in the dataset, and to forecast change-point groups with backpropagation neural networks (BPNs). In this stage, three change-point detection methods are applied and compared. They are: (1) the parametric approach, (2) the nonparametric approach, and (3) the model-based approach. The next stage is to forecast the final output with BPNs. Through the application to financial time series forecasting, we compare the proposed models with a neural network model alone and, in addition, determine which of three change-point detection methods performs better. Furthermore, we evaluate whether the proposed models play a role in clustering to reflect the time. Finally, this study examines the predictability of the integrated neural network models based on change-point detection.

Sign in / Sign up

Export Citation Format

Share Document