Biblio

Due to improving computational capacity of supercomputers, transmitting encrypted packets via one single network path is vulnerable to brute-force attacks. The versatile attackers secretly eavesdrop all the packets, classify packets into different streams, performs an exhaustive search for the decryption key, and extract sensitive personal information from the streams. However, new Internet Protocol (IP) brings great opportunities and challenges for preventing eavesdropping attacks. In this paper, we propose a Programming Protocol-independent Packet Processors (P4) based Network Immune Scheme (P4NIS) against the eavesdropping attacks. Specifically, P4NIS is equipped with three lines of defense to improve the network immunity. The first line is promiscuous forwarding by splitting all the traffic packets in different network paths disorderly. Complementally, the second line encrypts transmission port fields of the packets using diverse encryption algorithms. The encryption could distribute traffic packets from one stream into different streams, and disturb eavesdroppers to classify them correctly. Besides, P4NIS inherits the advantages from the existing encryption-based countermeasures which is the third line of defense. Using a paradigm of programmable data planes-P4, we implement P4NIS and evaluate its performances. Experimental results show that P4NIS can increase difficulties of eavesdropping significantly, and increase transmission throughput by 31.7% compared with state-of-the-art mechanisms.

The Software Defined Network (SDN) provides higher programmable functionality for network configuration and management dynamically. Moreover, SDN introduces a centralized management approach by dividing the network into control and data planes. In this paper, we introduce a deep learning enabled intrusion detection and prevention system (DL-IDPS) to prevent secure shell (SSH) brute-force attacks and distributed denial-of-service (DDoS) attacks in SDN. The packet length in SDN switch has been collected as a sequence for deep learning models to identify anomalous and malicious packets. Four deep learning models, including Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and Stacked Auto-encoder (SAE), are implemented and compared for the proposed DL-IDPS. The experimental results show that the proposed MLP based DL-IDPS has the highest accuracy which can achieve nearly 99% and 100% accuracy to prevent SSH Brute-force and DDoS attacks, respectively.

We propose a high efficiency Early-Complete Brute Force Elimination method that speeds up the analysis flow of the Camouflage Integrated Circuit (IC). The proposed method is targeted for security qualification of the Camouflaged IC netlists in Intellectual Property (IP) protection. There are two main features in the proposed method. First, the proposed method features immediate elimination of the incorrect Camouflage gates combination for the rest of computation, concentrating the resources into other potential correct Camouflage gates combination. Second, the proposed method features early complete, i.e. revealing the correct Camouflage gates once all incorrect gates combination are eliminated, increasing the computation speed for the overall security analysis. Based on the Python programming platform, we implement the algorithm of the proposed method and test it for three circuits including ISCAS’89 benchmarks. From the simulation results, our proposed method, on average, features 71% lesser number of trials and 79% shorter run time as compared to the conventional method in revealing the correct Camouflage gates from the Camouflaged IC netlist.

Today our world benefits from Internet of Things (IoT) technology; however, new security problems arise when these IoT devices are introduced into our homes. Because many of these IoT devices have access to the Internet and they have little to no security, they make our smart homes highly vulnerable to compromise. Some of the threats include IoT botnets and generic confidentiality, integrity, and availability (CIA) attacks. Our research explores botnet detection by experimenting with supervised machine learning and deep-learning classifiers. Further, our approach assesses classifier performance on unbalanced datasets that contain benign data, mixed in with small amounts of malicious data. We demonstrate that the classifiers can separate malicious activity from benign activity within a small IoT network dataset. The classifiers can also separate malicious activity from benign activity in increasingly larger datasets. Our experiments have demonstrated incremental improvement in results for (1) accuracy, (2) probability of detection, and (3) probability of false alarm. The best performance results include 99.9% accuracy, 99.8% probability of detection, and 0% probability of false alarm. This paper also demonstrates how the performance of these classifiers increases, as IoT training datasets become larger and larger.

Reliability analysis of concurrent data based on Botnet modeling is conducted in this paper. At present, the detection methods for botnets are mainly focused on two aspects. The first type requires the monitoring of high-privilege systems, which will bring certain security risks to the terminal. The second type is to identify botnets by identifying spam or spam, which is not targeted. By introducing multi-dimensional permutation entropy, the impact of permutation entropy on the permutation entropy is calculated based on the data communicated between zombies, describing the complexity of the network traffic time series, and the clustering variance method can effectively solve the difficulty of the detection. This paper is organized based on the data complex structure analysis. The experimental results show acceptable performance.

Mobile Ad hoc Network (MANET) is one of the emerging technologies to communicate between nodes and its decentralized structure, self-configuring nature are the few properties of this Ad hoc network. Due to its undefined structure, it has found its usage in the desired and temporary communication network. MANET has many routing protocols governing it and due to its changing topology, there can be many issues arise in recent times. Problems like no central node, limited energy, and the quality of service, performance, design issues, and security challenges have been bugging the researchers. The black hole attacks are the kind that cause ad hoc network to be at loss of information and make the source to believe that it has the actual least distance path to the destination, but in real scenario the packets do not get forwarded to neighbouring nodes. In this paper, we have discussed different solutions over the past years to deal with such attacks. A summary of the schemes with their results and drawbacks in terms of performance metrics is also given.

Although deep convolutional neural network (CNN) performs well in many computer vision tasks, its classification mechanism is very vulnerable when it is exposed to the perturbation of adversarial attacks. In this paper, we proposed a new algorithm to generate the substitute model of black-box CNN models by using knowledge distillation. The proposed algorithm distills multiple CNN teacher models to a compact student model as the substitution of other black-box CNN models to be attacked. The black-box adversarial samples can be consequently generated on this substitute model by using various white-box attacking methods. According to our experiments on ResNet18 and DenseNet121, our algorithm boosts the attacking success rate (ASR) by 20% by training the substitute model based on knowledge distillation.

The facial recognition time by time takes more importance, due to the extend kind of applications it has, but it is still challenging when faces big variations in the characteristics of the biometric data used in the process and especially referring to the transportation of information through the internet in the internet of things context. Based on the systematic review and rigorous study that supports the extraction of the most relevant information on this topic [1], a software architecture proposal which contains basic security requirements necessary for the treatment of the data involved in the application of facial recognition techniques, oriented to an IoT environment was generated. Concluding that the security and privacy considerations of the information registered in IoT devices represent a challenge and it is a priority to be able to guarantee that the data circulating on the network are only accessible to the user that was designed for this.

The rapid proliferation of biometrics has led to growing concerns about the security and privacy of the biometric data (template). A biometric uniquely identifies an individual and unlike passwords, it cannot be revoked or replaced since it is unique and fixed for every individual. To address this problem, many biometric template protection methods using fully homomorphic encryption have been proposed. But, most of them (i) are computationally expensive and practically infeasible (ii) do not support operations over real valued biometric feature vectors without quantization (iii) do not support packing of real valued feature vectors into a ciphertext (iv) require multi-shot enrollment of users for improved matching performance. To address these limitations, we propose a secure and privacy preserving method for biometric template protection using fully homomorphic encryption. The proposed method is computationally efficient and practically feasible, supports operations over real valued feature vectors without quantization and supports packing of real valued feature vectors into a single ciphertext. In addition, the proposed method enrolls the users using one-shot enrollment. To evaluate the proposed method, we use three face datasets namely LFW, FEI and Georgia tech face dataset. The encrypted face template (for 128 dimensional feature vector) requires 32.8 KB of memory space and it takes 2.83 milliseconds to match a pair of encrypted templates. The proposed method improves the matching performance by 3 % when compared to state-of-the-art, while providing high template security.

The blockchain's cross-chain atomic exchange uses smart contracts to replace trusted third parties, but atomic exchange cannot guarantee the anonymity of transactions, and it will inevitably increase the risk of privacy leakage. Therefore, this paper proposes an atom based on zero-knowledge proof. Improved methods of exchange to ensure the privacy of both parties in a transaction. The anonymous improvement scheme in this article uses the UTXO unconsumed model to add a new anonymous list in the blockchain. When sending assets to smart contracts, zero-knowledge proof is used to provide self-certification of ownership of the asset, and then the transaction is broken down. Only the hash value of the transaction is sent to the node, and the discarded list is used to verify the validity of the transaction, which achieves the effect of storing assets anonymously in the smart contract. At the same time, a smart contract is added when the two parties in the transaction communicate to exchange the contract address of the newly set smart contract between the two parties in the transaction. This can prevent the smart contract address information from being stolen when the two parties in the transaction communicate directly.

The 5G network solutions currently standardised and deployed do not yet enable the full potential of pervasive networking and computing envisioned in 5G initial visions: network services and slices with different QoS profiles do not span multiple operators; security, trust and automation is limited. The evolution of 5G towards a truly production-level stage needs to heavily rely on automated end-to-end network operations, use of distributed Artificial Intelligence (AI) for cognitive network orchestration and management and minimal manual interventions (zero-touch automation). All these elements are key to implement highly pervasive network infrastructures. Moreover, Distributed Ledger Technologies (DLT) can be adopted to implement distributed security and trust through Smart Contracts among multiple non-trusted parties. In this paper, we propose an initial concept of a zero-touch security and trust architecture for ubiquitous computing and connectivity in 5G networks. Our architecture aims at cross-domain security & trust orchestration mechanisms by coupling DLTs with AI-driven operations and service lifecycle automation in multi-tenant and multi-stakeholder environments. Three representative use cases are identified through which we will validate the work which will be validated in the test facilities at 5GBarcelona and 5TONIC/Madrid.

This paper presents hybrid system to minimize damage by zero-day attack. Proposed system consists of signature-based NIDPS, honeypot and temporary queue. When proposed system receives packet from external network, packet which is known for attack packet is dropped by signature-based NIDPS. Passed packets are redirected to honeypot, because proposed system assumes that all packets which pass NIDPS have possibility of zero-day attack. Redirected packet is stored in temporary queue and if the packet has possibility of zero-day attack, honeypot extracts signature of the packet. Proposed system creates rule that match rule format of NIDPS based on extracted signatures and updates the rule. After the rule update is completed, temporary queue sends stored packet to NIDPS then packet with risk of attack can be dropped. Proposed system can reduce time to create and apply rule which can respond to unknown attack packets. Also, it can drop packets that have risk of zero-day attack in real time.

It is now possible to synthesize highly realistic images of people who do not exist. Such content has, for example, been implicated in the creation of fraudulent socialmedia profiles responsible for dis-information campaigns. Significant efforts are, therefore, being deployed to detect synthetically-generated content. One popular forensic approach trains a neural network to distinguish real from synthetic content.We show that such forensic classifiers are vulnerable to a range of attacks that reduce the classifier to near- 0% accuracy. We develop five attack case studies on a state- of-the-art classifier that achieves an area under the ROC curve (AUC) of 0.95 on almost all existing image generators, when only trained on one generator. With full access to the classifier, we can flip the lowest bit of each pixel in an image to reduce the classifier's AUC to 0.0005; perturb 1% of the image area to reduce the classifier's AUC to 0.08; or add a single noise pattern in the synthesizer's latent space to reduce the classifier's AUC to 0.17. We also develop a black-box attack that, with no access to the target classifier, reduces the AUC to 0.22. These attacks reveal significant vulnerabilities of certain image-forensic classifiers.

To ensure quality of service and user experience, large Internet companies often monitor various Key Performance Indicators (KPIs) of their systems so that they can detect anomalies and identify failure in real time. However, due to a large number of various KPIs and the lack of high-quality labels, existing KPI anomaly detection approaches either perform well only on certain types of KPIs or consume excessive resources. Therefore, to realize generic and practical KPI anomaly detection in the real world, we propose a KPI anomaly detection framework named iRRCF-Active, which contains an unsupervised and white-box anomaly detector based on Robust Random Cut Forest (RRCF), and an active learning component. Specifically, we novelly propose an improved RRCF (iRRCF) algorithm to overcome the drawbacks of applying original RRCF in KPI anomaly detection. Besides, we also incorporate the idea of active learning to make our model benefit from high-quality labels given by experienced operators. We conduct extensive experiments on a large-scale public dataset and a private dataset collected from a large commercial bank. The experimental resulta demonstrate that iRRCF-Active performs better than existing traditional statistical methods, unsupervised learning methods and supervised learning methods. Besides, each component in iRRCF-Active has also been demonstrated to be effective and indispensable.

In Machine Learning, White Box Adversarial Attacks rely on knowing underlying knowledge about the model attributes. This works focuses on discovering to distrinct pieces of model information: the underlying architecture and primary training dataset. With the process in this paper, a structured set of input probes and the output of the model become the training data for a deep classifier. Two subdomains in Machine Learning are explored - image based classifiers and text transformers with GPT-2. With image classification, the focus is on exploring commonly deployed architectures and datasets available in popular public libraries. Using a single transformer architecture with multiple levels of parameters, text generation is explored by fine tuning off different datasets. Each dataset explored in image and text are distinguishable from one another. Diversity in text transformer outputs implies further research is needed to successfully classify architecture attribution in text domain.

We consider the problem of protecting cloud services from simultaneous white-box and black-box attacks. Recent research in cryptographic program obfuscation considers the problem of protecting the confidentiality of programs and any secrets in them. In this model, a provable program obfuscation solution makes white-box attacks to the program not more useful than black-box attacks. Motivated by very recent results showing successful black-box attacks to machine learning programs run by cloud servers, we propose and study the approach of augmenting the program obfuscation solution model so to achieve, in at least some class of application scenarios, program confidentiality in the presence of both white-box and black-box attacks.We propose and formally define encrypted-input program obfuscation, where a key is shared between the entity obfuscating the program and the entity encrypting the program's inputs. We believe this model might be of interest in practical scenarios where cloud programs operate over encrypted data received by associated sensors (e.g., Internet of Things, Smart Grid).Under standard intractability assumptions, we show various results that are not known in the traditional cryptographic program obfuscation model; most notably: Yao's garbled circuit technique implies encrypted-input program obfuscation hiding all gates of an arbitrary polynomial circuit; and very efficient encrypted-input program obfuscation for range membership programs and a class of machine learning programs (i.e., decision trees). The performance of the latter solutions has only a small constant overhead over the equivalent unobfuscated program.

Human identification is a well-researched topic that keeps evolving. Advancement in technology has made it easy to train models or use ones that have been already created to detect several features of the human face. When it comes to identifying a human face from the side, there are many opportunities to advance the biometric identification research further. This paper investigates the human face identification based on their side profile by extracting the facial features and diagnosing the feature sets with geometric ratio expressions. These geometric ratio expressions are computed into feature vectors. The last stage involves the use of weighted means to measure similarity. This research addresses the problem of using an eXplainable Artificial Intelligence (XAI) approach. Findings from this research, based on a small data-set, conclude that the used approach offers encouraging results. Further investigation could have a significant impact on how face profiles can be identified. Performance of the proposed system is validated using metrics such as Precision, False Acceptance Rate, False Rejection Rate and True Positive Rate. Multiple simulations indicate an Equal Error Rate of 0.89.

In modern high-performance computing (HPC) systems, network congestion is an important factor that contributes to performance degradation. However, how network congestion impacts application performance is not fully understood. As Aries network, a recent HPC network architecture featuring a dragonfly topology, is equipped with network counters measuring packet transmission statistics on each router, these network metrics can potentially be utilized to understand network performance. In this work, by experiments on a large HPC system, we quantify the impact of network congestion on various applications' performance in terms of execution time, and we correlate application performance with network metrics. Our results demonstrate diverse impacts of network congestion: while applications with intensive MPI operations (such as HACC and MILC) suffer from more than 40% extension in their execution times under network congestion, applications with less intensive MPI operations (such as Graph500 and HPCG) are mostly not affected. We also demonstrate that a stall-to-flit ratio metric derived from Aries network counters is positively correlated with performance degradation and, thus, this metric can serve as an indicator of network congestion in HPC systems.

Electricity has become the primary need of human life. The emerging of IoT concept recently in our lives, has offered the chance to establish energy efficient smart devices, systems and cities. Due to the urging need for conserving energy, this paper proposes an IoT based wireless energy efficient smart metering systems for smart cities. A network of smart meters is achieved to deliver the energy consumption data to the Energy/Utility provider. The star and mesh topologies are used in creating the network of smart meters in order to increase the distance of coverage. The proposed system offers an easily operated application for users as well as a Website and database for electricity Supplier Company. The proposed system design has an accuracy level of 95% and it is about 35% lower cost than its peer in the global market. The proposed design reduced the power consumption by 25%.

This paper investigates the use of BeagleBone Black Wireless single-board Linux computers with Long Range (LoRa) transceivers to send and receive information in a mesh network while one of the transmitting/receiving nodes is acting as a relay in the system. An experiment is conducted to examine how long each LoRa node needed to learn the transmission intervals of any other transmitting nodes on the network and to synchronize with the other nodes prior to transmission. The spread factor, bandwidth, and coding rate are all varied for a total of 18 different combinations. A link to the Python code used on the BeagleBone Black is provided at the end of this paper. The best parameter combinations for each individual node and for the system as a whole is investigated. Additional experiments and applications of this technology are explored in the conclusions.

Software Defined Vehicular Networking (SDVN) could be the future of the vehicular networks, enabling interoperability between heterogeneous networks and mobility management. Thus, the deployment of large SDVN is considered. However, SDVN is facing major security issues, in particular, authentication and access control issues. Indeed, an unauthorized SDN controller could modify the behavior of switches (packet redirection, packet drops) and an unauthorized switch could disrupt the operation of the network (reconnaissance attack, malicious feedback). Due to the SDVN features (decentralization, mobility) and the SDVN requirements (flexibility, scalability), the Blockchain technology appears to be an efficient way to solve these authentication and access control issues. Therefore, many Blockchain-based approaches have already been proposed. However, two key challenges have not been addressed: authentication and access control for SDN controllers and high scalability for the underlying Blockchain network. That is why in this paper we propose an innovative and scalable architecture, based on a set of interconnected Blockchain sub-networks. Moreover, an efficient access control mechanism and a cross-sub-networks authentication/revocation mechanism are proposed for all SDVN devices (vehicles, roadside equipment, SDN controllers). To demonstrate the benefits of our approach, its performances are compared with existing solutions in terms of throughput, latency, CPU usage and read/write access to the Blockchain ledger. In addition, we determine an optimal number of Blockchain sub-networks according to different parameters such as the number of certificates to store and the number of requests to process.

Device management in large networks is of growing importance to network administrators and security analysts alike. The composition of devices on a network can help forecast future traffic demand as well as identify devices that may pose a security risk. However, the sheer number and diversity of devices that comprise most modern networks have vastly increased the management complexity. Motivated by a need for an encryption-invariant device management strategy, we use affiliation graphs to develop a methodology that reveals key insights into the devices acting on a network using only the source and destination IP addresses. Through an empirical analysis of the devices on a university campus network, we provide an example methodology to infer a device's characteristics (e.g., operating system) through the services it communicates with via the Internet.

We investigate a prediction model using RNN for network intrusion detection in industrial IoT environments. For intrusion detection, we use anomaly detection methods that estimate the next packet, measure and score the distance measurement in real packets to distinguish whether it is a normal packet or an abnormal packet. When the packet was learned in the LSTM model, two-gram and sliding window of N-gram showed the best performance in terms of errors and the performance of the LSTM model was the highest compared with other data mining regression techniques. Finally, cosine similarity was used as a scoring function, and anomaly detection was performed by setting a boundary for cosine similarity that consider as normal packet.

With the rapid development of Internet, the issue of cyber security has increasingly gained more attention. An intrusion Detection System (IDS) is an effective technique to defend cyber-attacks and reduce security losses. However, the challenge of IDS lies in the diversity of cyber-attackers and the frequently-changing data requiring a flexible and efficient solution. To address this problem, machine learning approaches are being applied in the IDS field. In this paper, we propose an efficient scalable neural-network-based hybrid IDS framework with the combination of Host-level IDS (HIDS) and Network-level IDS (NIDS). We applied the autoencoders (AE) to NIDS and designed HIDS using word embedding and convolutional neural network. To evaluate the IDS, many experiments are performed on the public datasets NSL-KDD and ADFA. It can detect many attacks and reduce the security risk with high efficiency and excellent scalability.

The widespread application of 5G will make intrusion detection of large-scale network traffic a mere need. However, traditional intrusion detection cannot meet the requirements by manually extracting features, and the existing AI methods are also relatively inefficient. Therefore, when performing intrusion detection tasks, they have significant disadvantages of high false alarm rates and low recognition performance. For this challenge, this paper proposes a novel hybrid network, RULA-IDS, which can perform intrusion detection tasks by great amount statistical data from the network monitoring system. RULA-IDS consists of the fully connected layer, the feature extraction layer, the global attention mechanism layer and the SVM classification layer. In the feature extraction layer, the residual U-Net and LSTM are used to extract the spatial and temporal features of the network traffic attributes. It is worth noting that we modified the structure of U-Net to suit the intrusion detection task. The global attention mechanism layer is then used to selectively retain important information from a large number of features and focus on those. Finally, the SVM is used as a classifier to output results. The experimental results show that our method outperforms existing state-of-the-art intrusion detection methods, and the accuracies of training and testing are improved to 97.01% and 98.19%, respectively, and presents stronger robustness during training and testing.