Computer detection intelligent mining algorithm for software defined networks

In the field of launch vehicles, high launch density, heavy work intensity and large data volume have brought the traditional automatic anomaly detection with incomplete coverage, and complex design of criterion, which influencing performance evaluation of launch vehicle. In order to fully mine the data variation law implied in the massive telemetry data, the intelligent anomaly detection algorithm is proposed and designed as a beneficial supplement to the traditional anomaly detection algorithm, and improve the anomaly detection coverage and efficiency. With the telemetry data generated by the liquid launch vehicle taken as the research object, and the intelligent anomaly detection algorithm is compared with the traditional algorithm. It is shown that the algorithm proposed adapts to the anomaly detection scenarios with frequency anomaly and frame loss, which may be difficult for traditional algorithms to design anomaly detection criteria, and the average anomaly detection performance is improved by nearly 30% and the variance is reduced by 85%, providing a reference for improving anomaly detection system and applying intelligent anomaly detection algorithms in aerospace.

Purpose The authors argue that the current studies about malicious insiders confuse the fact that malicious attacks belong to two different categories, namely, those that launch instrumental attacks and expressive attacks. The authors collect malicious insider data from publicly available sources and use text-mining techniques to analyze the association between malicious insiders’ characteristics and the different types of attack. Design/methodology/approach The authors investigated the relationship between personality characteristics and different types of malicious attacks. For the personality characteristics, the authors use the same method as Liang et al. (2016), which extracted these characteristics based on a keyword-characteristic dictionary. For different types of malicious attacks, two raters rated each case based on criteria modified from criminology research to determine the degree of expressiveness and instrumentality. Findings The results show that malicious insiders who are manipulative or seeking personal gain tend to carry out instrumental attacks. Malicious insiders who are arrogant tend to conduct expressive attacks. Research limitations/implications This study uses third party articles to identify the personality characteristics of known malicious insiders. As such, not all personality characteristics may have been reported. Data availability was an issue. Practical implications Understanding if different personality characteristics lead different types of attacks can help managers identify employees who exhibit them and mitigate an attack before it occurs. Social implications Malicious insider attacks can have devastating results on businesses and employees. Help to identify potential malicious insiders before they act, may prevent undue harm. Originality/value This study used 132 cases of none malicious insiders to examine their attack objectives. No other study that the authors know of used that many cases.

Popularity of Software Defined Network (SDN) technology is spreading rapidly and corporate networks are deploying to take advantages of its features. Control & Data planes are segregated in SDN and simple forwarding devices enabled with OpenFlow protocol is used to forward data planes. The responsibility of control planes are taken by controller into SDN network. The data packets are generated by source host and forwarded to destination host by seeing destination address of such packet without validating source host address. Flow of data packets is controlled by controller setting up required flow entries into flow table of forwarding devices. Initially forwarding devices do not have any security & control and they are not able to forward traffic generated by attached hosts. Data packets of attached hosts are sent to the controller by forwarding devices for generation of control packets and setup necessary flow entries into device flow table. Source IP spoofed attacks may be setup by attacker in this situation and perform different type of attacks. There are some techniques for prevention and mitigation from such attacks. In this study, we offer an analysis of available source address validation techniques for SDN environment. The study discussed various features, limitations and gaps of source address validation solutions and provided various areas in SDN Security for future research.

Ship wake is an important military target, while the ocean background data in satellite images is huge, and ship wake targets are few. How to quickly and accurately find targets in large amounts of data is a valuable research topic. The ship wake target has a different detection method from the general target, as it has the characteristics of uniform background and prominent line characteristics. In this paper, we design a ship wake detection method which can quickly screen out easily detected samples by using traditional algorithms including Gaussian filtering, Canny edge detection and probabilistic Hough transform. We used typical representative YOLOv5 and Faster-R-CNN target detection frameworks to train single-stage and two-stage target detection models. In the process of integrating traditional algorithms into ship wake detection, we have built a ship wake target detection system that combines traditional algorithms with neural network methods. The experiment shows that the improved traditional wake detection algorithm can effectively improve the efficiency of ship wake detection system in target detection task.

Traditional Adaboost face detection algorithm uses Haar-like features training face classifiers, whose detection error rate is low in the face region. While under the complex background, the classifiers will make wrong detection easily to the background regions with the similar faces gray level distribution, which leads to the error detection rate of traditional Adaboost algorithm is high. As one of the most important features of a face, skin in YCgCr color space has good clustering. We can fast exclude the non-face areas through the skin color model. Therefore, combining with the advantages of the Adaboost algorithm and skin color detection algorithm, this paper proposes Adaboost face detection algorithm method that bases on YCgCr skin color model. Experiments show that, compared with traditional algorithm, the method we proposed has improved significantly in the detection accuracy and errors.

Attack-aware Security Function Management

谱峰的检测分析在色谱技术研究中具有十分重要的作用,但在色谱数据采集、传输的过程中,不同程度的噪声干扰给谱峰检测带来了极大的困难。目前传统的谱峰检测算法普遍通过基底扣除的方式对谱峰的形态进行预定义,将谱峰分为单峰、重叠峰等多个种类。针对不同种类的谱峰采用不同的检测方法,这就导致了传统的谱峰检测算法具有高复杂度、低自动化程度以及容易失真等缺点。因此,该文从另一个角度出发提出了一种新型的谱峰检测算法。该算法取消基底扣除以及谱峰分类这一步骤,直接在源数据曲线的基础上进行谱峰检测,主要分为离散差分、趋势累积以及遍历寻峰3个步骤。首先通过信号量表征数据升降趋势;然后进行数据趋势累积,根据累积总和定位谱峰,采用三点定位的方式,即峰起点、极值点和峰终点描述一个谱峰的位置;最后根据遍历排序的方式进行谱峰的筛选。此外,通过谱峰扣除的方式得到曲线基底部分。采用C语言设计编写了算法程序,并对多个动态比表面积分析仪测定的色谱图进行了检测分析,结果显示使用该算法可以精准区分谱峰部分与基底部分,受数据曲线毛刺、震荡等噪声干扰很小,谱峰的三点定位十分准确,且不受其复杂形态的影响,具有很强的普适性。与其他算法相比,该算法定位准确,结构清晰,具有较好的稳定性以及可靠性。该文报道了无基底扣除以及趋势累积等新型谱峰检测思想在吸脱附色谱曲线中的应用,证明了其在吸脱附色谱峰检测中的有效性和良好的应用前景。

In recent years, the fall detection system has become an important topic in the homecare system. Compared with the traditional fall detection algorithm, the method used by neural network is more robust and has higher accuracy. However neural network consumes a large amount of energy due to a huge number of computations, and needs more memory to store parameters as compared to traditional algorithms. In this paper, we propose a fall detection system in combination of the traditional algorithm with the neural network. First, we propose a skeleton information extraction algorithm, which transforms depth information into skeleton information and extracts the important joints related to fall activity. Also we have modified the skeleton-based method with seven highlight feature points. Second, we propose a highly robust deep convolution neural network architecture, which uses a pruning method to reduce parameters and calculations in the network. The low number of parameters and calculations makes the system suitable for the implementation on an embedded system. The experiment results show the high accuracy and robustness on the popular benchmark dataset NTU RGB+D. The proposed system has been implemented on NVIDIA Jetson Tx2 platform with real-time processing.

Infrared maritime target detection is a key technology for maritime target searching systems. However, in infrared maritime images (IMIs) taken under complicated sea conditions, background clutters, such as ocean waves, clouds or sea fog, usually have high intensity that can easily overwhelm the brightness of real targets, which is difficult for traditional target detection algorithms to deal with. To mitigate this problem, this paper proposes a novel target detection algorithm based on texture orientation. This algorithm first extracts suspected targets by analyzing the intersubband correlation between horizontal and vertical wavelet subbands of the original IMI on the first scale. Then the self-adaptive wavelet threshold denoising and local singularity analysis of the original IMI is combined to remove false alarms further. Experiments show that compared with traditional algorithms, this algorithm can suppress background clutter much better and realize better single-frame detection for infrared maritime targets. Besides, in order to guarantee accurate target extraction further, the pipeline-filtering algorithm is adopted to eliminate residual false alarms. The high practical value and applicability of this proposed strategy is backed strongly by experimental data acquired under different environmental conditions.

Software-defined networking (SDN) is a network technology that aims to make the network more flexible and centralized. The main aim of the architecture is decoupling of network and control plane which enables the network control to be programmed and hence the forwarding devices are abstracted from higher application services. However, before this technology evolves on a large scale, it is important to understand the vulnerabilities associated with it. The agenda for this paper is to study the different types of attacks on the three layers of the OpenFlow protocol and the possible mitigation strategies to reduce the impact of those attacks on the network, implement SDN network which consists assorted topologies connecting numerous hosts, switches, and controllers. The implemented framework monitors the various events occurring in the network, identifies malicious events causing DoS attack, and mitigates the same. Through implementation, we elaborate different ways of making SDN more secure.

In order to improve an efficiency of energy detection for a spectrum sensing in cognitive radio (CR), this paper proposes a dynamic threshold optimization algorithm. The traditional energy detection algorithm uses a fixed threshold, and can't guarantee always the optimal sensing performance in any environment. The improvement for sensing performance need to minimize the undetected probability and the probability of false alarm, and it is dissimilar for different CR users to accept these two errors. We improve the traditional energy detection algorithm, and firstly introduce a preference factor to characterize CR users’ different requirements for these two errors, then, propose a dynamic threshold optimization algorithm by minimizing integrated detection error for different signal-to-noise ratio (SNR). The simulation results show that the proposed algorithm effectively reduces the integrated spectrum sensing error, and increases the probability of detection, especially in low SNR.

Small targets in long-distance aerial photography have the problems of small size and blurry appearance, and traditional object detection algorithms face great challenges in the field of small-object detection. With the collection of massive data in the information age, traditional object detection algorithms have been gradually replaced by deep learning algorithms and have an advantage. In this paper, the YOLOV3-Tiny backbone network is augmented by using the pyramid structure of image features to achieve multi-level feature fusion prediction. In order to eliminate the loss of spatial feature information and hierarchical information caused by pooling operations in convolution processes and multi-scale operations in multi-layer structures, a spatial attention mechanism based on residual structure is proposed. At the same time, the idea of reinforcement learning is introduced to guide bounding box regression on the basis of the rough positioning of the native boundary regression strategy, and the variable IoU calculation method is used as the evaluation index of the reward function, and the boundary regression model based on the reward mechanism is proposed for fine adjustment. The VisDrone2019 data set was selected as the experimental data support. Experimental results show that the mAP value of the improved small-object detection model is 33.15%, which is 11.07% higher than that of the native network model, and the boundary regression accuracy is improved by 23.74%.

There are different types of adversarial attacks and defences for machine learning algorithms which makes assessing the robustness of an algorithm a daunting task. Moreover, there is an intrinsic bias in these adversarial attacks and defences to make matters worse. Here, we organise the problems faced: a) Model Dependence, b) Insufficient Evaluation, c) False Adversarial Samples, and d) Perturbation Dependent Results. Based on this, we propose a model agnostic adversarial robustness assessment method based on L0 and L∞ distance-based norms and the concept of robustness levels to tackle the problems. We validate our robustness assessment on several neural network architectures (WideResNet, ResNet, AllConv, DenseNet, NIN, LeNet and CapsNet) and adversarial defences for image classification problem. The proposed robustness assessment reveals that the robustness may vary significantly depending on the metric used (i.e., L0 or L∞). Hence, the duality should be taken into account for a correct evaluation. Moreover, a mathematical derivation and a counter-example suggest that L1 and L2 metrics alone are not sufficient to avoid spurious adversarial samples. Interestingly, the threshold attack of the proposed assessment is a novel L∞ black-box adversarial method which requires even more minor perturbation than the One-Pixel Attack (only 12% of One-Pixel Attack’s amount of perturbation) to achieve similar results. We further show that all current networks and defences are vulnerable at all levels of robustness, suggesting that current networks and defences are only effective against a few attacks keeping the models vulnerable to different types of attacks.

Intrusion detection System forms a vital component of internet security. To keep pace with the growing trends, there is a critical need to replace single layer detection technology with multi layer detection. Different types of Denial of Service (DoS) attacks thwart authorized users from gaining access to the networks and we tried to detect as well as alleviate some of those attacks. In this paper, we have proposed a novel cross layer intrusion detection architecture to discover the malicious nodes and different types of DoS attacks by exploiting the information available across different layers of protocol stack in order to improve the accuracy of detection. We have used cooperative anomaly intrusion detection with data mining technique to enhance the proposed architecture. We have implemented fixed width clustering algorithm for efficient detection of the anomalies in the MANET traffic and also generated different types of attacks in the network. The simulation of the proposed architecture is performed in OPNET simulator and we got the result as we expected.

Under low signal‐to‐clutter ratio (SCR) condition, the detection performance of traditional detection algorithm that detected in the signal level is poor, especially for moving the target. In this study, a new detection idea to detect in the data level is presented to improve the detection performance under low SCR condition. The new detection algorithm directly processes the measurement set generated by pre‐processing. On the basis of a binary hypothesis and the Bernoulli random finite set (B‐RFS), the authors proposed a B‐RFS detector, in which the probability of existence of target is treated as a test statistic of the binary hypothesis. As the information of multi‐frame is used, the detection performance will be better than the traditional detection algorithm. If the presence of the target is determined by the detector, they can obtain the estimation of the target state. The simulation results show that the proposed algorithm has better performance than traditional detection algorithm, and the performance of the algorithm is better with the increase of the processing time. Furthermore, the estimation of the target state is close to the true target state. As the proposed algorithm is detected in the data level, it can be applied to a variety of sensors.