Biblio

Malwares are the key means leveraged by threat actors in the cyber space for their attacks. There is a large array of commercial solutions in the market and significant scientific research to tackle the challenge of the detection and defense against malwares. At the same time, attackers also advance their capabilities in creating polymorphic and metamorphic malwares to make it increasingly challenging for existing solutions. To tackle this issue, we propose a methodology to perform malware detection and family attribution. The proposed methodology first performs the extraction of opcodes from malwares in each family and constructs their respective opcode graphs. We explore the use of clustering algorithms on the opcode graphs to detect clusters of malwares within the same malware family. Such clusters can be seen as belonging to different sub-family groups. Opcode graph signatures are built from each detected cluster. Hence, for each malware family, a group of signatures is generated to represent the family. These signatures are used to classify an unknown sample as benign or belonging to one the malware families. We evaluate our methodology by performing experiments on a dataset consisting of both benign files and malware samples belonging to a number of different malware families and comparing the results to existing approach.

With tons of efforts spent on its mitigation, Cross-site scripting (XSS) remains one of the most prevalent security threats on the internet. Decades of exploitation and remediation demonstrated that code inspection and testing alone does not eliminate XSS vulnerabilities in complex web applications with a high degree of confidence. This paper introduces Google's secure-by-design engineering paradigm that effectively prevents DOM-based XSS vulnerabilities in large-scale web development. Our approach, named API hardening, enforces a series of company-wide secure coding practices. We provide a set of secure APIs to replace native DOM APIs that are prone to XSS vulnerabilities. Through a combination of type contracts and appropriate validation and escaping, the secure APIs ensure that applications based thereon are free of XSS vulnerabilities. We deploy a simple yet capable compile-time checker to guarantee that developers exclusively use our hardened APIs to interact with the DOM. We make various of efforts to scale this approach to tens of thousands of engineers without significant productivity impact. By offering rigorous tooling and consultant support, we help developers adopt the secure coding practices as seamlessly as possible. We present empirical results showing how API hardening has helped reduce the occurrences of XSS vulnerabilities in Google's enormous code base over the course of two-year deployment.

E-commerce, ticket booking, banking, and other web-based applications that deal with sensitive information, such as passwords, payment information, and financial information, are widespread. Some web developers may have different levels of understanding about securing an online application. The two vulnerabilities identified by the Open Web Application Security Project (OWASP) for its 2017 Top Ten List are SQL injection and Cross-site Scripting (XSS). Because of these two vulnerabilities, an attacker can take advantage of these flaws and launch harmful web-based actions. Many published articles concentrated on a binary classification for these attacks. This article developed a new approach for detecting SQL injection and XSS attacks using deep learning. SQL injection and XSS payloads datasets are combined into a single dataset. The word-embedding technique is utilized to convert the word’s text into a vector. Our model used BiLSTM to auto feature extraction, training, and testing the payloads dataset. BiLSTM classified the payloads into three classes: XSS, SQL injection attacks, and normal. The results showed great results in classifying payloads into three classes: XSS attacks, injection attacks, and non-malicious payloads. BiLSTM showed high performance reached 99.26% in terms of accuracy.

Most famous malware defense tools depend on a large number of detect rules, which are time consuming to develop and require lots of professional experience. Meanwhile, even commercial tools may show high false-negative for some new coming malware, whose patterns were not curved in the prepared rules. This paper proposed the Normalized CNN based Malicious binary Detection method on condition of String, Feature mining (NCMDSF) to address the above problems. Firstly, amount of string feature was extracted from thousands of windows binary applications. Secondly, a 3-layer normalized CNN model, with normalization layer other than down sampling layer, was fit to detect malware. Finally, the proposed method NCMDSF was evaluated to discover malware from more than 1,000 windows binary applications by K-fold cross validation. Experimental results showed that, NCMDSF was superior to some other learning-based methods, including classical CNN, LSTM, normalized LSTM, and won higher true positive rate on the condition of same false positive rate. Furthermore, it successfully avoids over-fitting that occurs in deep learning methods without using normalization.

The security and privacy concerns along with the amount of data that is required to be processed on regular basis has pushed processing to the edge of the computing systems. Deploying advanced Neural Networks (NN), such as deep neural networks (DNNs) and spiking neural networks (SNNs), that offer state-of-the-art results on resource-constrained edge devices is challenging due to the stringent memory and power/energy constraints. Moreover, these systems are required to maintain correct functionality under diverse security and reliability threats. This paper first discusses existing approaches to address energy efficiency, reliability, and security issues at different system layers, i.e., hardware (HW) and software (SW). Afterward, we discuss how to further improve the performance (latency) and the energy efficiency of Edge AI systems through HW/SW-level optimizations, such as pruning, quantization, and approximation. To address reliability threats (like permanent and transient faults), we highlight cost-effective mitigation techniques, like fault-aware training and mapping. Moreover, we briefly discuss effective detection and protection techniques to address security threats (like model and data corruption). Towards the end, we discuss how these techniques can be combined in an integrated cross-layer framework for realizing robust and energy-efficient Edge AI systems.

In the current network security situation, the types of network threats are complex and changeable. With the development of the Internet and the application of information technology, the general trend is opener. Important data and important business applications will face more serious security threats. However, with the development of cloud computing technology, the trend of large-scale deployment of important business applications in cloud centers has greatly increased. The development and use of software-defined networks in cloud data centers have greatly reduced the effect of traditional network security boundary protection. How to find an effective way to protect important applications in open multi-step large-scale cloud data centers is a problem we need to solve. Threat intelligence has become an important means to solve complex network attacks, realize real-time threat early warning and attack tracking because of its ability to analyze the threat intelligence data of various network attacks. Based on the research of threat intelligence, machine learning, cloud central network, SDN and other technologies, this paper proposes an active defense method of network security based on threat intelligence for super-large cloud data centers.

Radar sensors have shown great potential for surveillance and security authentication applications. However, a thorough analysis of their vulnerability to spoofing or replay attacks has not been performed yet. In this paper, the feasibility of performing spoofing attacks to radar sensor is studied and experimentally verified. First, a simple binary phase-shift keying system was used to generate artificial spectral components in the radar's demodulated signal. Additionally, an analog phase shifter was driven by an arbitrary signal generator to mimic the human cardio-respiratory motion. Characteristic time and frequency domain cardio-respiratory human signatures were successfully generated, which opens possibilities to perform spoofing attacks to surveillance and security continuous authentication systems based on microwave radar sensors.

Wireless Sensor Networks (WSN) are gaining popularity as being the backbone of Cyber physical systems, IOT and various data acquisition from sensors deployed in remote, inaccessible terrains have remote deployment. However due to remote deployment, WSN is an adhoc network of large number of sensors either heli-dropped in inaccessible terrain like volcanoes, Forests, border areas are highly energy deficient and available in large numbers. This makes it the right soup to become vulnerable to various kinds of Security attacks. The lack of energy and resources makes it deprived of developing a robust security code for mitigation of various kinds of attacks. Many attempts have been made to suggest a robust security Protocol. But these consume so much energy, bandwidth, processing power, memory and other resources that the sole purpose of data gathering from inaccessible terrain from energy deprived sensors gets defeated. This paper makes an attempt to study the types of attacks on different layers of WSN and the examine the recent trends in development of various security protocols to mitigate the attacks. Further, we have proposed a simple, lightweight but powerful security protocol known as Simple Sensor Security Protocol (SSSP), which captures the uniqueness of WSN and its isolation from internet to develop an energy efficient security solution.

With the continuous improvement of China's scientific and technological level, computer network has become an indispensable part of people's daily life. It can not only effectively improve the efficiency of production and life, and shorten the distance between people, but also further promote the speed of China's social and economic development, which has a positive impact on the realization of China's modernization. Under the new information security demand environment at present, we should pay attention to the related information security work and formulate effective security measures and strategies. In order to effectively prevent these information security problems, people should actively adopt firewall technology, encryption technology, network access control technology and network virus prevention technology for effective protection. This paper analyzes the security problems in the application of wireless sensor networks and explores the mechanism of defending information security, hoping to strengthen the security and stability of wireless sensor networks through effective measures, so that people can better enjoy the convenience brought by the network age.

This paper studies the technology of generating DDPG (deep deterministic policy gradient) by using the deep dual network and experience pool network structure, and puts forward the sampling strategy gradient algorithm to randomly select actions according to the learned strategies (action distribution) in the continuous action space, based on the dispatching control system of the power dispatching control center of a super city power grid, According to the actual characteristics and operation needs of urban power grid, The developed refined artificial intelligence on-line security analysis and emergency response plan intelligent generation function realize the emergency response auxiliary decision-making intelligent generation function. According to the hidden danger of overload and overload found in the online safety analysis, the relevant load lines of the equipment are searched automatically. Through the topology automatic analysis, the load transfer mode is searched to eliminate or reduce the overload or overload of the equipment. For a variety of load transfer modes, the evaluation index of the scheme is established, and the optimal load transfer mode is intelligently selected. Based on the D5000 system of Metropolitan power grid, a multi-objective and multi resource coordinated security risk decision-making assistant system is implemented, which provides integrated security early warning and decision support for the main network and distribution network of city power grid. The intelligent level of power grid dispatching management and dispatching operation is improved. The state reality network can analyze the joint state observations from the action reality network, and the state estimation network uses the actor action as the input. In the continuous action space task, DDPG is better than dqn and its convergence speed is faster.

Firewall is the first defense line for network security. Packet filtering is a basic function in firewall, which filter network packets according to a series of rules called firewall policy. The design of firewall policy is invariably under the instruction of security policy, which is a generic guideline that lists the needs for network access permissions. The design of firewall policy should observe the regulations of security policy. However, even for IPv4 firewall policy, it is extremely difficult to keep the consistency between security policy and firewall policy. Some consistency decision methods of security policy and IPv4 firewall policy were proposed. However, the address space of IPv6 address is a very large, the existing consistency decision methods can not be directly used to deal with IPv6 firewall policy. To resolve the above problem, in this paper, we use a formal technique to decide the consistency between IPv6 firewall policy and security policy effectively and rapidly. We also developed a prototype model and evaluated the effectiveness of the proposed method.

With the widespread deployment of Internet of Things (IoT) devices, hackers can use IoT devices to launch large-scale distributed denial of service (DDoS) attacks, which bring great harm to the Internet. However, how to defend against these attacks remains to be an open challenge. In this paper, we propose a novel prevention method for IoT DDoS attacks based on blockchain and obfuscation of IP addresses. Our observation is that IoT devices are usually resource-constrained and cannot support complicated cryptographic algorithms such as RSA. Based on the observation, we employ a novel authentication then communication mechanism for IoT DDoS attack prevention. In this mechanism, the attack targets' IP addresses are encrypted by a random security parameter. Clients need to be authenticated to obtain the random security parameter and decrypt the IP addresses. In particular, we propose to authenticate clients with public-key cryptography and a blockchain system. The complex authentication and IP address decryption operations disable IoT devices and thus block IoT DDoS attacks. The effectiveness of the proposed method is analyzed and validated by theoretical analysis and simulation experiments.

This work investigates entropy-based prevention of Distributed Denial-of-Service (DDoS) attacks for Software Defined Networks (SDN). The experiments are conducted on a virtual SDN testbed setup within Mininet, a Linux-based network emulator. An arms race iterates on the SDN testbed between offense, launching botnet-based DDoS attacks with progressive sophistications, and defense who is deploying SDN controls with emerging technologies from other faucets of cyber engineering. The investigation focuses on the transmission control protocol’s synchronize flood attack that exploits vulnerabilities in the three-way TCP handshake protocol, to lock up a host from serving new users.The defensive strategy starts with a common packet filtering-based design from the literature to mitigate attacks. Utilizing machine learning algorithms, SDNs actively monitor all possible traffic as a collective dataset to detect DDoS attacks in real time. A constant upgrade to a stronger defense is necessary, as cyber/network security is an ongoing front where attackers always have the element of surprise. The defense further invests on entropy methods to improve early detection of DDoS attacks within the testbed environment. Entropy allows SDNs to learn the expected normal traffic patterns for a network as a whole using real time mathematical calculations, so that the SDN controllers can sense the distributed attack vectors building up before they overwhelm the network.This work reveals the vulnerabilities of SDNs to stealthy DDoS attacks and demonstrates the effectiveness of deploying entropy in SDN controllers for detection and mitigation purposes. Future work includes provisions to use these entropy detection methods, as part of a larger system, to redirect traffic and protect networks dynamically in real time. Other types of DoS, such as ransomware, will also be considered.

Distributed denial of service (DDoS) attack is a common way of network attack. It has the characteristics of wide distribution, low cost and difficult defense. The traditional algorithms of machine learning (ML) have such shortcomings as excessive systemic overhead and low accuracy in detection of DDoS. In this paper, a CGAN (conditional generative adversarial networks, conditional GAN) -based method is proposed to detect the attack of DDoS. On off-line training, five features are extracted in order to adapt the input of neural network. On the online recognition, CGAN model is adopted to recognize the packets of DDoS attack. The experimental results demonstrate that our proposed method obtains the better performance than the random forest-based method.

DDoS attack detection in a single dimension cannot cope with complex and new attacks. Aiming at the problems existing in single dimension detection, this paper proposes an algorithm to detect DDoS attack based on multi-dimensional entropy. Firstly, the algorithm selects multiple dimensions and establishes corresponding decision function for each dimension and calculates its information entropy. Secondly, the multidimensional sliding window CUSUM algorithm without parameters is used to synthesize the detection results of three dimensions to determine whether it is attacked by DDoS. Finally, the data set published by MIT Lincoln Laboratory is used for testing. Experimental results show that compared with single dimension detection algorithm, this method has good detection rate and low false alarm rate.

With the maturity of Internet of things technology, massive data transmission has become the focus of research. In order to solve the problem of low speed of traditional hybrid data fast distribution algorithm for wireless sensor networks, a hybrid data fast distribution algorithm for wireless sensor networks based on visual Internet of things is designed. The logic structure of mixed data input gate in wireless sensor network is designed through the visual Internet of things. The objective function of fast distribution of mixed data in wireless sensor network is proposed. The number of copies of data to be distributed is dynamically calculated and the message deletion strategy is determined. Then the distribution parameters are calibrated, and the fitness ranking is performed according to the distribution quantity to complete the algorithm design. The experimental results show that the distribution rate of the designed algorithm is significantly higher than that of the control group, which can solve the problem of low speed of traditional data fast distribution algorithm.

Aiming at the working mechanism of optical backbone network, based on the theory of complex network, the invulnerability evaluation index of optical backbone network is extracted from the physical topology of optical backbone network and the degree of bandwidth satisfaction, finally, the invulnerability evaluation model of optical backbone network is established. At the same time, the evaluation model is verified and analyzed with specific cases, through the comparison of 4 types of attack, the results show that the number of deliberate point attacks ( DP) is 16.7% lower than that of random point attacks ( RP) when the critical collapse state of the network is reached, and the number of deliberate edge attacks ( DE) is at least 10.4% lower than that of random edge attacks ( RE). Therefore, evaluating the importance of nodes and edges and strengthening the protection of key nodes and edges can help optical network effectively resist external attacks and significantly improve the anti-damage ability of optical network, which provides theoretical support for the anti-damage evaluation of optical network and has certain practical significance for the upgrade and reconstruction of optical network.

With the advance in artificial intelligence and high-dimensional data analysis, federated learning (FL) has emerged to allow distributed data providers to collaboratively learn without direct access to local sensitive data. However, limiting access to individual provider’s data inevitably incurs security issues. For instance, backdoor attacks, one of the most popular data poisoning attacks in FL, severely threaten the integrity and utility of the FL system. In particular, backdoor attacks launched by multiple collusive attackers, i.e., distributed backdoor attacks, can achieve high attack success rates and are hard to detect. Existing defensive approaches, like model inspection or model sanitization, often require to access a portion of local training data, which renders them inapplicable to the FL scenarios. Recently, the norm clipping approach is developed to effectively defend against distributed backdoor attacks in FL, which does not rely on local training data. However, we discover that adversaries can still bypass this defense scheme through robust training due to its unchanged norm clipping threshold. In this paper, we propose a novel defense scheme to resist distributed backdoor attacks in FL. Particularly, we first identify that the main reason for the failure of the norm clipping scheme is its fixed threshold in the training process, which cannot capture the dynamic nature of benign local updates during the global model’s convergence. Motivated by it, we devise a novel defense mechanism to dynamically adjust the norm clipping threshold of local updates. Moreover, we provide the convergence analysis of our defense scheme. By evaluating it on four non-IID public datasets, we observe that our defense scheme effectively can resist distributed backdoor attacks and ensure the global model’s convergence. Noticeably, our scheme reduces the attack success rates by 84.23% on average compared with existing defense schemes.

Performance measures commonly used in systems security engineering tend to be static, linear, and have limited utility in addressing challenges to security performance from increasingly complex risk environments, adversary innovation, and disruptive technologies. Leveraging key concepts from resilience science offers an opportunity to advance next-generation systems security engineering to better describe the complexities, dynamism, and nonlinearity observed in security performance—particularly in response to these challenges. This article introduces a multilayer network model and modified Continuous Time Markov Chain model that explicitly captures interdependencies in systems security engineering. The results and insights from a multilayer network model of security for a hypothetical nuclear power plant introduce how network-based metrics can incorporate resilience concepts into performance metrics for next generation systems security engineering.

Industrial Internet is widely used in the production field. As the openness of networks increases, industrial networks facing increasing security risks. Information and communication technologies are now available for most industrial manufacturing. This industry-oriented evolution has driven the emergence of cloud systems, the Internet of Things (IoT), Big Data, and Industry 4.0. However, new technologies are always accompanied by security vulnerabilities, which often expose unpredictable risks. Industrial safety has become one of the most essential and challenging requirements. In this article, we highlight the serious challenges facing Industry 4.0, introduce industrial security issues and present the current awareness of security within the industry. In this paper, we propose solutions for the anomaly detection and defense of the industrial Internet based on the demand characteristics of network security, the main types of intrusions and their vulnerability characteristics. The main work is as follows: This paper first analyzes the basic network security issues, including the network security needs, the security threats and the solutions. Secondly, the security requirements of the industrial Internet are analyzed with the characteristics of industrial sites. Then, the threats and attacks on the network are analyzed, i.e., system-related threats and process-related threats; finally, the current research status is introduced from the perspective of network protection, and the research angle of this paper, i.e., network anomaly detection and network defense, is proposed in conjunction with relevant standards. This paper proposes a software-defined network (SDN)-based industrial Internet security gateway for the security protection of the industrial Internet. Since there are some known types of attacks in the industrial network, in order to fully exploit the effective information, we combine the ExtratreesClassifier to enhance the detection rate of anomaly detection. In order to verify the effectiveness of the algorithm, this paper simulates an industrial network attack, using the acquired training data for testing. The test data are industrial network traffic datasets, and the experimental results show that the algorithm is suitable for anomaly detection in industrial networks.

This paper proposes an artificial immune information security protection technology architecture for embedded system of Electric power equipment. By simulating the three functions of human immunity, namely "immune homeostasis", "immune surveillance" and "immune defense", the power equipment is endowed with the ability of human like active immune security protection. Among them, "immune homeostasis" is constructed by trusted computing technology components to establish a trusted embedded system running environment. Through fault-tolerant component construction, "immune surveillance" and "immune defense" realize illegal data defense, business logic legitimacy check and equipment status evaluation, realize real-time perception and evaluation of power equipment's own security status, as well as fault emergency handling and event backtracking record, so that power equipment can realize self recovery from abnormal status. The proposed technology architecture is systematic, scientific and rich in scalability, which can significantly improve the information security protection ability of electric power equipment.

Security baseline hardening is a baseline configuration framework aims to improve the robustness of the operating system, lowering the risk and impact of breach incidents. In typical best practice, the security baseline hardening requires to have regular check and follow-up to keep the system in-check, this set of activities are called "Security Baseline Audit". The Security Baseline Audit process is responsible by the IT department. In terms of business, this process consumes a fair number of resources such as man-hour, time, and technical knowledge. In a huge production environment, the resources mentioned can be multiplied by the system's amount in the production environment. This research proposes improving the process with automation while maintaining the quality and security level at the standard. Robot Framework, a useful and flexible opensource automation framework, is being utilized in this research following with a very successful result where the configuration is aligned with CIS (Center for Internet Security) run by the automation process. A tremendous amount of time and process are decreased while the configuration is according to this tool's standard.

In recent years, more and more medical institutions have been using electronic medical records (EMRs) to improve service efficiency and reduce storage cost. However, it is difficult for medical institutions with different management methods to share medical data. The medical data of patients is easy to be abused, and there are security risks of privacy data leakage. The above problems seriously impede the sharing of medical data. To solve these problems, we propose a blockchain-based medical data sharing scheme with attribute-based searchable encryption, named BMDS. In BMDS, encrypted EMRs are securely stored in the interplanetary file system (IPFS), while corresponding indexes and other information are stored in a medical consortium blockchain. The proposed BMDS has the features of tamper-proof, privacy preservation, verifiability and secure key management, and there is no single point of failure. The performance evaluation of computational overhead and security analysis show that the proposed BMDS has more comprehensive security features and practicability.

In the distributed file sharing system, a large number of users share bandwidth, upload resources and store them in a decentralized manner, thus offering both an abundant supply of high-quality resources and high-speed download. However, some users only enjoy the convenient service without uploading or sharing, which is called free riding. Free-riding may discourage other honest users. When free-riding users mount to a certain number, the platform may fail to work. The current available incentive mechanisms, such as reciprocal incentive mechanisms and reputation-based incentive mechanisms, which suffer simple incentive models, inability to achieve incentive circulation and dependence on a third-party trusted agency, are unable to completely solve the free-riding problem.In this paper we build a blockchain-based distributed file sharing platform and design a nested incentive scheme for this platform. The proposed nested incentive mechanism achieves the circulation of incentives in the platform and does not rely on any trusted third parties for incentive distribution, thus providing a better solution to free-riding. Our distributed file sharing platform prototype is built on the current mainstream blockchain. Nested incentive scheme experiments on this platform verify the effectiveness and superiority of our incentive scheme in solving the free-riding problem compared to other schemes.

Security, efficiency and availability are three key factors that affect the application of searchable encryption schemes in mobile cloud computing environments. In order to meet the above characteristics, this paper proposes a certificateless public key encryption with a keyword search (CLPEKS) scheme. In this scheme, a CLPEKS generation method and a Trapdoor generation method are designed to support multiple receivers to query. Based on the elliptic curve scalar multiplication, the efficiencies of encrypting keywords, generating Trapdoors, and testing are improved. By adding a random number factor to the Trapdoor generation, the scheme can resist the internal keyword guessing attacks. Under the random oracle model, it is proved that the scheme can resist keyword guessing attacks. Theoretical analyses and implementation show that the proposed scheme is more efficient than the existing schemes.