Deep support vector machine for hyperspectral image classification

Industrial information integration engineering (IIIE) is a set of foundational concepts and techniques that facilitate the industrial information integration process. In recent years, many applicat...

A Survey on Industrial Information Integration 2016–2019

The problem of low rate attack detection has been well studied in different situations. However the methods suffer to achieve higher performance in low rate attack detection. The multimedia transmission is focused on transmitting video and audio which claims higher bandwidth conditions. There exists no such algorithm in detecting low rate attacks for invariant network conditions. To solve this issue, an invariant feature based approach is presented in this paper. The method maintains the network features like the routes, bandwidth conditions and traffic. Based on these features, a set of routes has been identified for each data transmission. Here, low rate attack detection is performed at the reception of any packet and the data transmission is performed using cooperative routing. From the packet features, and the route being followed, the method identifies the class of route, traffic and bandwidth conditions of the route. Using these features, the method computes Network Transmission Support measure. Based on the NTS value, the method performs low rate attack detection and improves the performance.

Invariant packet feature with network conditions for efficient low rate attack detection in multimedia networks for improved QoS

The salient features of cloud computing (such as on-demand self-service, resource pooling, broad network access, rapid elasticity, and measured service) are being exploited by attackers to launch the severe Distributed Denial of Service (DDoS) attack. Generally, the DDoS attacks in such an environment have been implemented by flooding a huge volume (high-rate) of malicious traffic to exhaust the victim servers’ resources. Due to this huge volume of malicious traffic, such attacks can be easily detected. Thus, attackers are getting attracted towards the low-rate DDoS attacks, slowly. Low-rate DDoS attacks are difficult to detect due to their stealthy and low-rate traffic. In the recent years, many efforts have been devoted to defend against the low-rate DDoS attacks. By utilizing the salient features of cloud computing, it becomes easy for an attacker to launch sophisticated low-rate DDoS attacks. Thus, the study of various DDoS attacks and their corresponding defense approaches becomes essential to protect the cloud infrastructure from fatal effects of DDoS attacks. This paper presents a comprehensive taxonomy of all the possible variants of cloud DDoS attacks solutions with detailed insight into the characterization, prevention, detection, and mitigation mechanisms. The paper provides a detailed discussion on essential performance metrics to evaluate various defense solutions and their behavior in a cloud environment. The purpose of this survey paper is to excite the cloud security researchers to develop effective defense solutions against the various DDoS attacks. The research gaps and challenges are found, and described in the paper while future research directions are outlined.

Defense Mechanisms Against DDoS Attacks in a Cloud Computing Environment: State-of-the-Art and Research Challenges

Low-rate denial of service (LDoS) attacks send periodic pulse sequences with relative low rate to form aggregation flows at the victim end. LDoS attack flows have the characteristics of low average rate and great concealment. It is hard to detect LDoS attack flows from normal traffic due to low rate property. Network traffic measurement shows that aggregate network traffic is multifractal. In order to characterize and analyze network traffic, researchers have developed concise mathematical models to explore complex multifractal structure. Although the LDoS attack flows are very small, it will inevitably lead to the change of multifractal characteristics of network traffic. This paper targets at exploiting and estimating the changes in multifractal characteristics of network traffic for detecting LDoS attack flows. The algorithm of multifractal detrended fluctuation analysis (MF-DFA) is used to explore the change in terms of multifractal characteristics over a small scale of network traffic due to LDoS attacks. Through wavelet analysis, the singularity and bursty of network traffic under LDoS attacks are estimated by using Holder exponent. The difference values (D-value) of Holder exponent of network traffic between normal and under LDoS attack situations are calculated. The D-value is used as the basis to determine LDoS attacks. A detection threshold is set based on the statistical results. The presence of LDoS attacks can be confirmed through comparing D-value with detection threshold. Experiments on detection performance have been performed in the test-bed network and simulation platform. The extensive experimental results are congruent with the theoretical analysis.

Low-Rate DoS Attacks Detection Based on Network Multifractal

The shrew distributed denial of service (DDoS) attack is very detrimental for many applications, since it can throttle TCP flows to a small fraction of their ideal rate at very low attack cost. Earlier works mainly focused on empirical studies of defending against the shrew DDoS, and very few of them provided analytic results about the attack itself. In this paper, we propose a mathematical model for estimating attack effect of this stealthy type of DDoS. By originally capturing the adjustment behaviors of victim TCPs congestion window, our model can comprehensively evaluate the combined impact of attack pattern (i.e., how the attack is configured) and network environment on attack effect (the existing models failed to consider the impact of network environment). Henceforth, our model has higher accuracy over a wider range of network environments. The relative error of our model remains around 10% for most attack patterns and network environments, whereas the relative error of the benchmark model in previous works has a mean value of 69.57%, and it could be more than 180% in some cases. More importantly, our model reveals some novel properties of the shrew attack from the interaction between attack pattern and network environment, such as the minimum cost formula to launch a successful attack, and the maximum effect formula of a shrew attack. With them, we are able to find out how to adaptively tune the attack parameters (e.g., the DoS burst length) to improve its attack effect in a given network environment, and how to reconfigure the network resource (e.g., the bottleneck buffer size) to mitigate the shrew DDoS with a given attack pattern. Finally, based on our theoretical results, we put forward a simple strategy to defend the shrew attack. The simulation results indicate that this strategy can remarkably increase TCP throughput by nearly half of the bottleneck bandwidth (and can be higher) for general attack patterns.

On a Mathematical Model for Low-Rate Shrew DDoS

Multi-model ensemble with rich spatial information for object detection

An enterprise's data can be one of its most important assets and often critical to the firm's development and survival. SQL injection attack is ranked first in the top ten risks to network applications by the Open Web Application Security Project (OWASP). Its harmfulness, universality, and severe situation are self-evident. This paper presents a method of SQL injection detection based on Elastic-Pooling CNN (EP-CNN) and compares it with traditional detection methods. This method can output a fixed two-dimensional matrix without truncating data and effectively detects the SQL injection of web applications. Based on the irregular matching characteristics, it can identify new attacks and is harder to bypass.

/pdf/sql-injection-detection-for-web-applications-based-on-ucdq81nev0.pdf

SQL Injection Detection for Web Applications Based on Elastic-Pooling CNN

Nano-electrochemical cytosensors have attracted intensive attention and achieved huge progress in the biomedical field owing to their stability, rapidity, accuracy, and low-cost properties. Currently, most nano-electrochemical cytosensors are prepared using metal nanoparticles or carbon nanomaterials. In application, the nano-electrochemical cytosensors immobilize a bio-sensitive substance on the electrode, and convert the target molecule and its reaction signal into an electrical signal through specific recognition between the biomolecules, thereby achieving detection. Using nano-electrochemical cytosensors can help diagnose disease quickly and accurately, which could contribute to early diagnosis and clinical analysis. In this review, we concentrate on the latest development in metal nanoparticle and carbon nanomaterial based nano-electrochemical cytosensors in the last three years. Finally, we summarize the development of cytosensors and propose the future development prospects.

Nanomaterials in electrochemical cytosensors

At present, the market of network-based family health management is undergoing a fast growth and predicted to be extremely huge in the near future. Integration between traditional digital device in a family and common healthcare products can lead to a new strategy for family health management. Hereby, we imbed blood glucose monitoring function into a normal TV remote controller, which serves as a glucometer. In addition to normal function of TV remote controller, the proposed device can also serve as a medical device glucometer. The buried electrochemical module in TV remote controller is capable of resolving the current generated by a disposable glucose test strip. The retrieved blood glucose information is transmitted and displayed on TV, which can be further transferred to online personal health management center via network. Comparative study on reliability and accuracy between the integrated device and clinical biochemical analyzer shows good agreement. Taking account of rising concerns on daily healthcare, the proposed device holds great potentials in medical data acquisition for family-based health management.

Jie Xu

Papers

On a Mathematical Model for Low-Rate Shrew DDoS

Multi-model ensemble with rich spatial information for object detection

SQL Injection Detection for Web Applications Based on Elastic-Pooling CNN

Nanomaterials in electrochemical cytosensors

Family-Based Big Medical-Level Data Acquisition System