Biblio

Internet service providers (ISP) rely on network traffic classifiers to provide secure and reliable connectivity for their users. Encrypted traffic introduces a challenge as attacks are no longer viable using classic Deep Packet Inspection (DPI) techniques. Distinguishing encrypted from non-encrypted traffic is the first step in addressing this challenge. Several attempts have been conducted to identify encrypted traffic. In this work, we compare the detection performance of DPI, traffic pattern, and randomness tests to identify encrypted traffic in different levels of granularity. In an experimental study, we evaluate these candidates and show that a traffic pattern-based classifier outperforms others for encryption detection.

Network attacks become more complicated with the improvement of technology. Traditional statistical methods may be insufficient in detecting constantly evolving network attack. For this reason, the usage of payload-based deep packet inspection methods is very significant in detecting attack flows before they damage the system. In the proposed method, features are extracted from the byte distributions in the payload and these features are provided to characterize the flows more deeply by using N-Gram analysis methods. The proposed procedure has been tested on IDS 2012 and 2017 datasets, which are widely used in the literature.

This paper studies Distributed Denial of Service (DDoS) attack detection by adopting the Deep Neural Network (DNN) model in Software Defined Networking (SDN). We first deploy the flow collector module to collect the flow table entries. Considering the detection efficiency of the DNN model, we also design some features manually in addition to the features automatically obtained by the flow table. Then we use the preprocessed data to train the DNN model and make a prediction. The overall detection framework is deployed in the SDN controller. The experiment results illustrate DNN model has higher accuracy in identifying attack traffic than machine learning algorithms, which lays a foundation for the defense against DDoS attack.

This paper mainly explores the detection and defense of DDoS attacks in the SDN architecture of the 5G environment, and proposes a DDoS attack detection method based on the deep learning two-level model CNN-LSTM in the SDN network. Not only can it greatly improve the accuracy of attack detection, but it can also reduce the time for classifying and detecting network traffic, so that the transmission of DDoS attack traffic can be blocked in time to ensure the availability of network services.

Network security is a prominent topic that is gaining international attention. Distributed Denial of Service (DDoS) attack is often regarded as one of the most serious threats to network security. Software Defined Network (SDN) decouples the control plane from the data plane, which can meet various network requirements. But SDN can also become the object of DDoS attacks. This paper proposes an automated DDoS attack mitigation method that is based on the programmability of the Ryu controller and the features of the OpenFlow switch flow tables. The Mininet platform is used to simulate the whole process, from SDN traffic generation to using a K-Nearest Neighbor model for traffic classification, as well as identifying and mitigating DDoS attack. The packet counts of the victim's malicious traffic input port are significantly lower after the mitigation method is implemented than before the mitigation operation. The purpose of mitigating DDoS attack is successfully achieved.

One of the major threats in the cyber security and networking world is a Distributed Denial of Service (DDoS) attack. With massive development in Science and Technology, the privacy and security of various organizations are concerned. Computer Intrusion and DDoS attacks have always been a significant issue in networked environments. DDoS attacks result in non-availability of services to the end-users. It interrupts regular traffic flow and causes a flood of flooded packets, causing the system to crash. This research presents a Machine Learning-based DDoS attack detection system to overcome this challenge. For the training and testing purpose, we have used the NSL-KDD Dataset. Logistic Regression Classifier, Support Vector Machine, K Nearest Neighbour, and Decision Tree Classifier are examples of machine learning algorithms which we have used to train our model. The accuracy gained are 90.4, 90.36, 89.15 and 82.28 respectively. We have added a feature called BOTNET Prevention, which scans for Phishing URLs and prevents a healthy device from being a part of the botnet.

Deep learning models rely on single word features and location features of text to achieve good results in text relation extraction tasks. However, previous studies have failed to make full use of semantic information contained in sentence dependency syntax trees, and data sparseness and noise propagation still affect classification models. The BERT(Bidirectional Encoder Representations from Transformers) pretrained language model provides a better representation of natural language processing tasks. And entity enhancement methods have been proved to be effective in relation extraction tasks. Therefore, this paper proposes a combination of the shortest dependency path and entity-enhanced BERT pre-training language model for model construction to reduce the impact of noise terms on the classification model and obtain more semantically expressive feature representation. The algorithm is tested on SemEval-2010 Task 8 English relation extraction dataset, and the F1 value of the final experiment can reach 0. 881.

The value and size of information exchanged through dark-web pages are remarkable. Recently Many researches showed values and interests in using machine-learning methods to extract security-related useful knowledge from those dark-web pages. In this scope, our goals in this research focus on evaluating best prediction models while analyzing traffic level data coming from the dark web. Results and analysis showed that feature selection played an important role when trying to identify the best models. Sometimes the right combination of features would increase the model’s accuracy. For some feature set and classifier combinations, the Src Port and Dst Port both proved to be important features. When available, they were always selected over most other features. When absent, it resulted in many other features being selected to compensate for the information they provided. The Protocol feature was never selected as a feature, regardless of whether Src Port and Dst Port were available.

Multi-label image classification task aims to predict multiple object labels in a given image and faces the challenge of variable-sized objects. Limited by the size of CNN convolution kernels, existing CNN-based methods have difficulty capturing global dependencies and effectively fusing multiple layers features, which is critical for this task. Recently, transformers have utilized multi-head attention to extract feature with long range dependencies. Inspired by this, this paper proposes a Cross-layer Aggregation with Transformers (CAT) framework, which leverages transformers to capture the long range dependencies of CNN-based features with Long Range Dependencies module and aggregate the features layer by layer with Cross-Layer Fusion module. To make the framework efficient, a multi-head pre-max attention is designed to reduce the computation cost when fusing the high-resolution features of lower-layers. On two widely-used benchmarks (i.e., VOC2007 and MS-COCO), CAT provides a stable improvement over the baseline and produces a competitive performance.

As a mature and open mobile operating system, Android runs on many IoT devices, which has led to Android-based IoT devices have become a hotbed of malware. Existing static detection methods for malware using artificial intelligence algorithms focus only on the java code layer when extracting API features, however there is a lot of malicious behavior involving native layer code. Thus, to make up for the neglect of the native code layer, we propose a heterogeneous information network-based Android malware detection method with cross-layer features. We first translate the semantic information of apps and API calls into the form of meta-paths, and construct the adjacency of apps based on API calls, then combine information from different meta-paths using multi-core learning. We implemented our method on the dataset from VirusShare and AndroZoo, and the experimental results show that the accuracy of our method is 93.4%, which is at least 2% higher than other related methods using heterogeneous information networks for malware detection.

Intrusion detection for Controller Area Network (CAN) protocol requires modern methods in order to compete with other electrical architectures. Fingerprint Intrusion Detection Systems (IDS) provide a promising new approach to solve this problem. By characterizing network traffic from known ECUs, hazardous messages can be discriminated. In this article, a modified version of Fingerprint IDS is employed utilizing both step response and spectral characterization of network traffic via neural network training. With the addition of feature set reduction and hyperparameter tuning, this method accomplishes a 99.4% detection rate of trusted ECU traffic.

Modern connected vehicles are equipped with a large number of sensors, which enable a wide range of services that can improve overall traffic safety and efficiency. However, remote access to connected vehicles also introduces new security issues affecting both inter and intra-vehicle communications. In fact, existing intra-vehicle communication systems, such as Controller Area Network (CAN), lack security features, such as encryption and secure authentication for Electronic Control Units (ECUs). Instead, Original Equipment Manufacturers (OEMs) seek security through obscurity by keeping secret the proprietary format with which they encode the information. Recently, it has been shown that the reuse of CAN frame IDs can be exploited to perform CAN bus reverse engineering without physical access to the vehicle, thus raising further security concerns in a connected environment. This work investigates whether anonymizing the frames of each newly released vehicle is sufficient to prevent CAN bus reverse engineering based on frame ID matching. The results show that, by adopting Machine Learning techniques, anonymized CAN frames can still be fingerprinted and identified in an unknown vehicle with an accuracy of up to 80 %.

Most of the recent high-profile attacks targeting cyber-physical systems (CPS) started with lengthy reconnaissance periods that enabled attackers to gain in-depth understanding of the victim’s environment. To simulate these stealthy attacks, several covert channel tools have been published and proven effective in their ability to blend into existing CPS communication streams and have the capability for data exfiltration and command injection.In this paper, we report a novel machine learning feature engineering and data processing pipeline for the detection of covert channel attacks on CPS systems with real-time detection throughput. The system also operates at the network layer without requiring physical system domain-specific state modeling, such as voltage levels in a power generation system. We not only demonstrate the effectiveness of using TCP payload entropy as engineered features and the technique of grouping information into network flows, but also pitch the proposed detector against scenarios employing advanced evasion tactics, and still achieve above 99% detection performance.

For a long time, online attacks were regarded to pose a severe threat to web - based applications, websites, and clients. It can bypass authentication methods, steal sensitive information from datasets and clients, and also gain ultimate authority of servers. A variety of ways for safeguarding online apps have been developed and used to deal the website risks. Based on the studies about the intersection of cybersecurity and machine learning, countermeasures for identifying typical web assaults have recently been presented (ML). In order to establish a better understanding on this essential topic, it is necessary to study ML methodologies, feature extraction techniques, evaluate datasets, and performance metrics utilised in a systematic manner. In this paper, we go through web security flaws like SQLi, XSS, malicious URLs, phishing attacks, path traversal, and CMDi in detail. We also go through the existing security methods for detecting these threats using machine learning approaches for URL classification. Finally, we discuss potential research opportunities for ML and DL-based techniques in this category, based on a thorough examination of existing solutions in the literature.

While acquiring precise and intelligent state sensing and control capabilities, the cyber physical power system is constantly exposed to the potential cyber-attack threat. False data injection (FDI) attack attempts to disrupt the normal operation of the power system through the coupling of cyber side and physical side. To deal with the situation that stealthy FDI attack can bypass the bad data detection and thus trigger false commands, a system feature extraction method in state estimation is proposed, and the corresponding FDI attack detection method is presented. Based on the principles of state estimation and stealthy FDI attack, we analyze the impacts of FDI attack on measurement residual. Gaussian fitting method is used to extract the characteristic parameters of residual distribution as the system feature, and attack detection is implemented in a sliding time window by comparison. Simulation results prove that the proposed attack detection method is effectiveness and efficiency.

This article analyzes the current situation of computer network security in colleges and universities, future development trends, and the relationship between software vulnerabilities and worm outbreaks. After analyzing a server model with buffer overflow vulnerabilities, a worm implementation model based on remote buffer overflow technology is proposed. Complex networks are the medium of worm propagation. By analyzing common complex network evolution models (rule network models, ER random graph model, WS small world network model, BA scale-free network model) and network node characteristics such as extraction degree distribution, single source shortest distance, network cluster coefficient, richness coefficient, and close center coefficient.

Vulnerability discovery is an important field of computer security research and development today. Because most of the current vulnerability discovery methods require large-scale manual auditing, and the code parsing process is cumbersome and time-consuming, the vulnerability discovery effect is reduced. Therefore, for the uncertainty of vulnerability discovery itself, it is the most basic tool design principle that auxiliary security analysts cannot completely replace them. The purpose of this paper is to study the source code vulnerability discovery method based on graph neural network. This paper analyzes the three processes of data preparation, source code vulnerability mining and security assurance of the source code vulnerability mining method, and also analyzes the suspiciousness and particularity of the experimental results. The empirical analysis results show that the types of traditional source code vulnerability mining methods become more concise and convenient after using graph neural network technology, and we conducted a survey and found that more than 82% of people felt that the design source code vulnerability mining method used When it comes to graph neural networks, it is found that the design efficiency has become higher.

Cognitive Radio (CR) is an attractive solution in mobile communication for solving the spectrum scarcity problem. Moreover, security concerns are not yet fully satisfied. This article focuses on attacks such as the Primary user emulation attack (PUE) and the jammer attack. These attacks create anomalous spectrum access thereby disturbing the dynamic spectrum usage in the CR networks. A framework based on cross-layer has been designed effectively to determine these attacks in the CR networks. First, each secondary user will sense the spectrum in the physical layer and construct a feature space. Using the extracted features, the clusters are formed effectively for each user. In the network layer, multipath routing is employed to discover the routes for the secondary user. If the node in the path identifies any spectrum shortage, it will verify that location with the help of constructed cluster. If the node does not belong to any of the clusters, then it will be identified as the attacker node. Simulation results and security analysis are performed using the NS2 simulations, which show improvement in detection of the attacks, decrease in the detection delay, and less route dis-connectivity. The proposed cross-layer framework identifies the anomalous spectrum access attack effectively.

In this cyber era, the number of cybercrime problems grows significantly, impacting network communication security. Some factors have been identified, such as malware. It is a malicious code attack that is harmful. On the other hand, a botnet can exploit malware to threaten whole computer networks. Therefore, it needs to be handled appropriately. Several botnet activity detection models have been developed using a classification approach in previous studies. However, it has not been analyzed about selecting features to be used in the learning process of the classification algorithm. In fact, the number and selection of features implemented can affect the detection accuracy of the classification algorithm. This paper proposes an analysis technique for determining the number and selection of features developed based on previous research. It aims to obtain the analysis of using features. The experiment has been conducted using several classification algorithms, namely Decision tree, k-NN, Naïve Bayes, Random Forest, and Support Vector Machine (SVM). The results show that taking a certain number of features increases the detection accuracy. Compared with previous studies, the results obtained show that the average detection accuracy of 98.34% using four features has the highest value from the previous study, 97.46% using 11 features. These results indicate that the selection of the correct number and features affects the performance of the botnet detection model.

Visual Question Answering or VQA is a technique used in diverse domains ranging from simple visual questions and answers on short videos to security. Here in this paper, we talk about the video captcha that will be deployed for user authentication. Randomly any short video of length 10 to 20 seconds will be displayed and automated questions and answers will be generated by the system using AI and ML. Automated Programs have maliciously affected gateways such as login, registering etc. Therefore, in today's environment it is necessary to deploy such security programs that can recognize the objects in a video and generate automated MCQs real time that can be of context like the object movements, color, background etc. The features in the video highlighted will be recorded for generating MCQs based on the short videos. These videos can be random in nature. They can be taken from any official websites or even from your own local computer with prior permission from the user. The format of the video must be kept as constant every time and must be cross checked before flashing it to the user. Once our system identifies the captcha and determines the authenticity of a user, the other website in which the user wants to login, can skip the step of captcha verification as it will be done by our system. A session will be maintained for the user, eliminating the hassle of authenticating themselves again and again for no reason. Once the video will be flashed for an IP address and if the answers marked by the user for the current video captcha are correct, we will add the information like the IP address, the video and the questions in our database to avoid repeating the same captcha for the same IP address. In this paper, we proposed the methodology of execution of the aforementioned and will discuss the benefits and limitations of video captcha along with the visual questions and answering.

This paper presents CaptchaGG, a model for recognizing linear graphical CAPTCHAs. As in the previous society, CAPTCHA is becoming more and more complex, but in some scenarios, complex CAPTCHA is not needed, and usually, linear graphical CAPTCHA can meet the corresponding functional scenarios, such as message boards of websites and registration of accounts with low security. The scheme is based on convolutional neural networks for feature extraction of CAPTCHAs, recurrent neural forests A neural network that is too complex will lead to problems such as difficulty in training and gradient disappearance, and too simple will lead to underfitting of the model. For the single problem of linear graphical CAPTCHA recognition, the model which has a simple architecture, extracting features by convolutional neural network, sequence modeling by recurrent neural network, and finally classification and recognition, can achieve an accuracy of 96% or more recognition at a lower complexity.

Blind identification of channel codes is crucial in intelligent communication and non-cooperative signal processing, and it plays a significant role in wireless physical layer security, information interception, and information confrontation. Previous researches show a high computation complexity by manual feature extractions, in addition, problems of indisposed accuracy and poor robustness are to be resolved in a low signal-to-noise ratio (SNR). For solving these difficulties, based on deep residual shrinkage network (DRSN), this paper proposes a novel recognizer by deep learning technologies to blindly distinguish the type and the parameter of channel codes without any prior knowledge or channel state, furthermore, feature extractions by the neural network from codewords can avoid intricate calculations. We evaluated the performance of this recognizer in AWGN, single-path fading, and multi-path fading channels, the results of the experiments showed that the method we proposed worked well. It could achieve over 85 % of recognition accuracy for channel codes in AWGN channels when SNR is not lower than 4dB, and provide an improvement of more than 5% over the previous research in recognition accuracy, which proves the validation of the proposed method.

The cutting-edge biometric recognition systems extract distinctive feature vectors of biometric samples using deep neural networks to measure the amount of (dis-)similarity between two biometric samples. Studies have shown that personal information (e.g., health condition, ethnicity, etc.) can be inferred, and biometric samples can be reconstructed from those feature vectors, making their protection an urgent necessity. State-of-the-art biometrics protection solutions are based on homomorphic encryption (HE) to perform recognition over encrypted feature vectors, hiding the features and their processing while releasing the outcome only. However, this comes at the cost of those solutions' efficiency due to the inefficiency of HE-based solutions with a large number of multiplications; for (dis-)similarity measures, this number is proportional to the vector's dimension. In this paper, we tackle the HE performance bottleneck by freeing the two common (dis-)similarity measures, the cosine similarity and the squared Euclidean distance, from multiplications. Assuming normalized feature vectors, our approach pre-computes and organizes those (dis-)similarity measures into lookup tables. This transforms their computation into simple table-lookups and summation only. We study quantization parameters for the values in the lookup tables and evaluate performances on both synthetic and facial feature vectors for which we achieve a recognition performance identical to the non-tabularized baseline systems. We then assess their efficiency under HE and record runtimes between 28.95ms and 59.35ms for the three security levels, demonstrating their enhanced speed.

Smart phones have become the preferred way for Chinese Internet users currently. The mobile phone traffic is large from the operating system. These traffic is mainly generated by the services. In the context of the universal encryption of the traffic, classification identification of mobile encryption services can effectively reduce the difficulty of analytical difficulty due to mobile terminals and operating system diversity, and can more accurately identify user access targets, and then enhance service quality and network security management. The existing mobile encryption service classification methods have two shortcomings in feature selection: First, the DL model is used as a black box, and the features of large dimensions are not distinguished as input of classification model, which resulting in sharp increase in calculation complexity, and the actual application is limited. Second, the existing feature selection method is insufficient to use the time and space associated information of traffic, resulting in less robustness and low accuracy of the classification. In this paper, we propose a feature enhancement method based on adjacent flow contextual features and evaluate the Apple encryption service traffic collected from the real world. Based on 5 DL classification models, the refined classification accuracy of Apple services is significantly improved. Our work can provide an effective solution for the fine management of mobile encryption services.

Speech recognition technology has been applied to all aspects of our daily life, but it faces many security issues. One of the major threats is the adversarial audio examples, which may tamper the recognition results of the acoustic speech recognition system (ASR). In this paper, we propose an adversarial detection framework to detect adversarial audio examples. The method is based on the transformer self-attention mechanism. Spectrogram features are extracted from the audio and divided into patches. Position information are embedded and then fed into transformer encoder. Experimental results show that the method achieves good performance with the detection accuracy of above 96.5% under the white-box attacks and blackbox attacks, and noisy circumstances. Even when detecting adversarial examples generated by the unknown attacks, it also achieves satisfactory results.