Biblio

In defense and security applications, detection of moving target direction is as important as the target detection and/or target classification. In this study, a methodology for the detection of different mobile targets as approaching or receding was proposed for ground surveillance radar data, and convolutional neural networks (CNN) based on transfer learning were employed for this purpose. In order to improve the classification performance, the use of two key concepts, namely Deep Convolutional Generative Adversarial Network (DCGAN) and decision fusion, has been proposed. With DCGAN, the number of limited available data used for training was increased, thus creating a bigger training dataset with identical distribution to the original data for both moving directions. This generated synthetic data was then used along with the original training data to train three different pre-trained deep convolutional networks. Finally, the classification results obtained from these networks were combined with decision fusion approach. In order to evaluate the performance of the proposed method, publicly available RadEch dataset consisting of eight ground target classes was utilized. Based on the experimental results, it was observed that the combined use of the proposed DCGAN and decision fusion methods increased the detection accuracy of moving target for person, vehicle, group of person and all target groups, by 13.63%, 10.01%, 14.82% and 8.62%, respectively.

Smart cities deploy large numbers of sensors and collect a tremendous amount of data from them. For example, Advanced Metering Infrastructures (AMIs), which consist of physical meters that collect usage data about public utilities such as power and water, are an important building block in a smart city. In a typical sensor network, the measurement devices are connected through a computer network, which exposes them to cyber attacks. Furthermore, the data is centrally managed at the operator’s servers, making it vulnerable to insider threats.Our goal is to protect the integrity of data collected by large-scale sensor networks and the firmware in measurement devices from cyber attacks and insider threats. To this end, we first develop a comprehensive threat model for attacks against data and firmware integrity, which can target any of the stakeholders in the operation of the sensor network. Next, we use our threat model to analyze existing defense mechanisms, including signature checks, remote firmware attestation, anomaly detection, and blockchain-based secure logs. However, the large size of the Trusted Computing Base and a lack of scalability limit the applicability of these existing mechanisms. We propose the Feather-Light Blockchain Infrastructure (FLBI) framework to address these limitations. Our framework leverages a two-layer architecture and cryptographic threshold signature chains to support large networks of low-capacity devices such as meters and data aggregators. We have fully implemented the FLBI’s end-to-end functionality on the Hyperledger Fabric and private Ethereum blockchain platforms. Our experiments show that the FLBI is able to support millions of end devices.

FPGA bitstream protection schemes are often the first line of defense for secure hardware designs. In general, breaking the bitstream encryption would enable attackers to subvert the confidentiality and infringe on the IP. Or breaking the authenticity enables manipulating the design, e.g., inserting hardware Trojans. Since FPGAs see widespread use in our interconnected world, such attacks can lead to severe damages, including physical harm. Recently we [1] presented a surprising attack — Starbleed — on Xilinx 7-Series FPGAs, tricking an FPGA into acting as a decryption oracle. For their UltraScale(+) series, Xilinx independently upgraded the security features to AES-GCM, RSA signatures, and a periodic GHASH-based checksum to validate the bitstream during decryption. Hence, UltraScale(+) devices were considered not affected by Starbleed-like attacks [2], [1].We identified novel security weaknesses in Xilinx UltraScale(+) FPGAs if configured outside recommended settings. In particular, we present four attacks in this situation: two attacks on the AES encryption and novel GHASH-based checksum and two authentication downgrade attacks. As a major contribution, we show that the Starbleed attack is still possible within the UltraScale(+) series by developing an attack against the GHASH-based checksum. After describing and analyzing the attacks, we list the subtle configuration changes which can lead to security vulnerabilities and secure configurations not affected by our attacks. As Xilinx only recommends configurations not affected by our attacks, users should be largely secure. However, it is not unlikely that users employ settings outside the recommendations, given the rather large number of configuration options and the fact that Security Misconfiguration is among the leading top 10 OWASP security issues. We note that these security weaknesses shown in this paper had been unknown before.

Confidentiality and integrity security are the key challenges in future 5G networks. To encounter these challenges, various signature and key agreement protocols are being implemented in 5G systems to secure high-speed mobile-to-mobile communication. Many security ciphers such as SNOW 3G, Advanced Encryption Standard (AES), and ZUC are used for 5G security. Among these protocols, the AES algorithm has been shown to achieve higher hardware efficiency and throughput in the literature. In this paper, we implement the AES algorithm on Field Programmable Gate Array (FPGA) and real-time performance factors of the AES algorithm were exploited to best fit the needs and requirements of 5G. In addition, several modifications such as partial pipelining and deep pipelining (partial pipelining with sub-module pipelining) are implemented on Virtex 6 FPGA ML60S board to improve the throughput of the proposed design.

With the proliferation of malware, the detection and classification of malware have been hot topics in the academic and industrial circles of cyber security, and the generation of malware signatures is one of the important research directions. In this paper, we propose NBP-MS, a method of signature generation that is based on network traffic generated by malware. Specifically, we utilize the network traffic generated by malware to perform fine-grained profiling of its network behaviors first, and then cluster all the profiles to generate network behavior signatures to classify malware, providing support for subsequent analysis and defense.

SaaS is a cloud-based application service that allows users to use applications that work in a cloud environment. SaaS is a subscription type, and the service expenditure varies depending on the license, the number of users, and duration of use. For efficient network management, security and cost management, accurate detection of user behavior for SaaS applications is required. In this paper, we propose a rule-based traffic analysis method for the user behavior detection. We conduct comparative experiments with signature-based method by using the real SaaS application and demonstrate the validity of the proposed method.

The attacker’s server plays an important role in sending attack orders and receiving stolen information, particularly in the more recent cyberattacks. Under these circumstances, it is important to use network-based signatures to block malicious communications in order to reduce the damage. However, in addition to blocking malicious communications, signatures are also required not to block benign communications during normal business operations. Therefore, the generation of signatures requires a high level of understanding of the business, and highly depends on individual skills. In addition, in actual operation, it is necessary to test whether the generated signatures do not interfere with benign communications, which results in high operational costs. In this paper, we propose SIGMA, a system that automatically generates signatures to block malicious communication without interfering with benign communication and then automatically evaluates the impact of the signatures. SIGMA automatically extracts the common parts of malware communication destinations by clustering them and generates multiple candidate signatures. After that, SIGMA automatically calculates the impact on normal communication based on business logs, etc., and presents the final signature to the analyst, which has the highest blockability of malicious communication and non-blockability of normal communication. Our objectives with this system are to reduce the human factor in generating the signatures, reduce the cost of the impact evaluation, and support the decision of whether to apply the signatures. In the preliminary evaluation, we showed that SIGMA can automatically generate a set of signatures that detect 100% of suspicious URLs with an over-detection rate of just 0.87%, using the results of 14,238 malware analyses and actual business logs. This result suggests that the cost for generation of signatures and the evaluation of their impact on business operations can be suppressed, which used to be a time-consuming and human-intensive process.

Aiming at the prevention of information security risk in protection and control of smart substation, a multi-level security defense method of substation based on data aggregation and convolution neural network (CNN) is proposed. Firstly, the intelligent electronic device(IED) uses "digital certificate + digital signature" for the first level of identity authentication, and uses UKey identification code for the second level of physical identity authentication; Secondly, the device group of the monitoring layer judges whether the data report is tampered during transmission according to the registration stage and its own ID information, and the device group aggregates the data using the credential information; Finally, the convolution decomposition technology and depth separable technology are combined, and the time factor is introduced to control the degree of data fusion and the number of input channels of the network, so that the network model can learn the original data and fused data at the same time. Simulation results show that the proposed method can effectively save communication overhead, ensure the reliable transmission of messages under normal and abnormal operation, and effectively improve the security defense ability of smart substation.

The availability of FPGAs in cloud data centers offers rapid, on-demand access to hardware compute resources that users can configure to their own needs. However, the low-level access to the hardware FPGA and associated resources such as PCIe, SSD, or DRAM also opens up threats of malicious attackers uploading designs that are able to infer information about other users or about the cloud infrastructure itself. In particular, this work presents a new, fast PCIe-contention-based channel that is able to transmit data between different FPGA-accelerated virtual machines with bandwidths reaching 2 kbps with 97% accuracy. This paper further demonstrates that the PCIe receiver circuits are able to not just receive covert transmissions, but can also perform fine-grained monitoring of the PCIe bus or detect different types of activities from other users' FPGA-accelerated virtual machines based on their PCIe traffic signatures. Beyond leaking information across different virtual machines, the ability to monitor the PCIe bandwidth over hours or days can be used to estimate the data center utilization and map the behavior of the other users. The paper also introduces further novel threats in FPGA-accelerated instances, including contention due to shared NVMe SSDs as well as thermal monitoring to identify FPGA co-location using the DRAM modules attached to the FPGA boards. This is the first work to demonstrate that it is possible to break the separation of privilege in FPGA-accelerated cloud environments, and highlights that defenses for public clouds using FPGAs need to consider PCIe, SSD, and DRAM resources as part of the attack surface that should be protected.

Web application firewalls (WAF) are the last line of defense in protecting web applications from application layer security threats like SQL injection and cross-site scripting. Currently, most evasion techniques from WAFs are still developed manually. In this work, we propose a solution, which automatically scans the WAFs to find payloads through which the WAFs can be bypassed. Our solution finds out rules defects, which can be further used in rule tuning for rule-based WAFs. Also, it can enrich the machine learning-based dataset for retraining. To this purpose, we provide a framework based on reinforcement learning with an environment compatible with OpenAI gym toolset standards, employed for training agents to implement WAF evasion tasks. The framework acts as an adversary and exploits a set of mutation operators to mutate the malicious payload syntactically without affecting the original semantics. We use Q-learning and proximal policy optimization algorithms with the deep neural network. Our solution is successful in evading signature-based and machine learning-based WAFs.

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 meteoric advancement in quantum computing, the traditional data integrity verifying schemes are no longer safe for cloud data storage. A large number of the current techniques are dependent on expensive Public Key Infrastructure (PKI). They cost computationally and communicationally heavy for verification which do not stand with the advantages when quantum computing techniques are applied. Hence, a quantum safe and efficient integrity verification protocol is a research hotspot. Lattice-based signature constructions involve matrix-matrix or matrix vector multiplications making computation competent, simple and resistant to quantum computer attacks. Study in this paper uses Bloom Filter which offers high efficiency in query and search operations. Further, we propose an Identity-Based Integrity Verification (IBIV) protocol for cloud storage from Lattice and Bloom filter. We focus on security against attacks from Cloud Service Provider (CSP), data privacy attacks against Third Party Auditor (TPA) and improvement in efficiency.

Authorship attribution, an NLP problem where anonymous text is matched to its author, has important, cross-disciplinary applications, particularly those concerning cyber-defense. Our research examines the degree of sensitivity that attention-based models have to adversarial perturbations. We ask, what is the minimal amount of change necessary to maximally confuse a transformer model? In our investigation we examine a balanced subset of emails from the Enron email dataset, calculating the performance of our model before and after email signatures have been perturbed. Results show that the model's performance changed significantly in the absence of a signature, indicating the importance of email signatures in email authorship detection. Furthermore, we show that these models rely on signatures for shorter emails much more than for longer emails. We also indicate that additional research is necessary to investigate stylometric features and adversarial training to further improve classification model robustness.

Antivirus software is considered to be the primary line of defense against malicious software in modern computing systems. The purpose of this paper is to expose exploitation that can evade Antivirus software that uses signature-based detection algorithms. In this paper, a novel approach was proposed to change the source code of a common Metasploit-Framework used to compile the reverse shell payload without altering its functionality but changing its signature. The proposed method introduced an additional stage to the shellcode program. Instead of the shellcode being generated and stored within the program, it was generated separately and stored on a remote server and then only accessed when the program is executed. This approach was able to reduce its detectability by the Antivirus software by 97% compared to a typical reverse shell program.

Malicious hackers breach security perimeters, cause infrastructure disruptions as well as steal proprietary information, financial data, and violate consumers' privacy. Protection of the whole organization by using the firm's security officers can be besieged with faulty warnings. Engineers must shift from console to console to put together investigative clues as a result of today's fragmented security technologies that cause frustratingly sluggish investigations. Endpoint Detection and Response (EDR) solutions adds an extra layer of protection to prevent an endpoint action into a breach. EDR is the region's foremost detection and response tool that combines endpoint and network data to recognize and respond to sophisticated threats. Offering unrivaled security and operational effectiveness, it integrates prevention, investigation, detection, and responding in a single platform. EDR provides enterprise coverage and uninterrupted defense with its continuous monitoring and response to threats. We have presented a comprehensive review of existing EDRs through various security layers that includes detection, response and management capabilities which enables security teams to have unified end-to-end corporate accessibility, powerful analytics along with additional features such as web threat scan, external device scan and automatic reaction across the whole technological tower.

Content blocking is an important part of a per-formant, user-serving, privacy respecting web. Current content blockers work by building trust labels over URLs. While useful, this approach has many well understood shortcomings. Attackers may avoid detection by changing URLs or domains, bundling unwanted code with benign code, or inlining code in pages.The common flaw in existing approaches is that they evaluate code based on its delivery mechanism, not its behavior. In this work we address this problem by building a system for generating signatures of the privacy-and-security relevant behavior of executed JavaScript. Our system uses as the unit of analysis each script's behavior during each turn on the JavaScript event loop. Focusing on event loop turns allows us to build highly identifying signatures for JavaScript code that are robust against code obfuscation, code bundling, URL modification, and other common evasions, as well as handle unique aspects of web applications.This work makes the following contributions to the problem of measuring and improving content blocking on the web: First, we design and implement a novel system to build per-event-loop-turn signatures of JavaScript behavior through deep instrumentation of the Blink and V8 runtimes. Second, we apply these signatures to measure how much privacy-and-security harming code is missed by current content blockers, by using EasyList and EasyPrivacy as ground truth and finding scripts that have the same privacy and security harming patterns. We build 1,995,444 signatures of privacy-and-security relevant behaviors from 11,212 unique scripts blocked by filter lists, and find 3,589 unique scripts hosting known harmful code, but missed by filter lists, affecting 12.48% of websites measured. Third, we provide a taxonomy of ways scripts avoid detection and quantify the occurrence of each. Finally, we present defenses against these evasions, in the form of filter list additions where possible, and through a proposed, signature based system in other cases.As part of this work, we share the implementation of our signature-generation system, the data gathered by applying that system to the Alexa 100K, and 586 AdBlock Plus compatible filter list rules to block instances of currently blocked code being moved to new URLs.

In this study, a novel decentralized authentication model is proposed for establishing a secure communications structure in VoIP applications. The proposed scheme considers a distributed architecture called the blockchain. With this scheme, we highlight the multimedia data is more resistant to some of the potential attacks according to the centralized architecture. Our scheme presents the overall system authentication architecture, and it is suitable for mutual authentication in terms of privacy and anonymity. We construct an ECC-based model in the encryption infrastructure because our structure is time-constrained during communications. This study differs from prior work in that blockchain platforms with ECC-Based Biometric Signature. We generate a biometric key for creating a unique ID value with ECC to verify the caller and device authentication together in blockchain. We validated the proposed model by comparing with the existing method in VoIP application used centralized architecture.

Security analysts conduct continuous evaluations of cyber-defense tools to keep pace with advanced and persistent threats. Cyber agility has become a critical proactive security resource that makes it possible to measure defense adjustments and reactions to rising threats. Subsequently, machine learning has been applied to support cyber agility prediction as an essential effort to anticipate future security performance. Nevertheless, apt and treacherous actors motivated by economic incentives continue to prevail in circumventing machine learning-based protection tools. Adversarial learning, widely applied to computer security, especially intrusion detection, has emerged as a new area of concern for the recently recognized critical cyber agility prediction. The rationale is, if a sophisticated malicious actor obtains the cyber agility parameters, correct prediction cannot be guaranteed. Unless with a demonstration of white-box attack failures. The challenge lies in recognizing that unconstrained adversaries hold vast potential capabilities. In practice, they could have perfect-knowledge, i.e., a full understanding of the defense tool in use. We address this challenge by proposing an adversarial machine learning approach that achieves accurate cyber agility forecast through mapped nefarious influence on static defense tools metrics. Considering an adversary would aim at influencing perilous confidence in a defense tool, we demonstrate resilient cyber agility prediction through verified attack signatures in dynamic learning windows. After that, we compare cyber agility prediction under negative influence with and without our proposed dynamic learning windows. Our numerical results show the model's execution degrades without adversarial machine learning. Such a feigned measure of performance could lead to incorrect software security patching.

With the proliferation of Mobile Internet, handheld devices are facing continuous threats from apps that contain malicious intents. These malicious apps, or malware, have the capability of dynamically changing their intended code as they spread. Moreover, the diversity and volume of their variants severely undermine the effectiveness of traditional defenses, which typically use signature-based techniques, and make them unable to detect the previously unknown malware. However, the variants of malware families share typical behavioral patterns reflecting their origin and purpose. The behavioral patterns, obtained either statically or dynamically, can be exploited to detect and classify unknown malware into their known families using machine learning techniques. In this paper, we propose a new approach for detecting and analyzing a malware. Mainly focused on android apps, our approach adopts the two following steps: (1) performs a transformation of an APK file into a lightweight RGB image using a predefined dictionary and intelligent mapping, and (2) trains a convolutional neural network on the obtained images for the purpose of signature detection and malware family classification. The results obtained using the Androzoo dataset show that our system classifies both legacy and new malware apps with high accuracy, low false-negative rate (FNR), and low false-positive rate (FPR).

Analyzing the DNS traffic of Internet hosts has been a successful technique to counter cyberattacks and identify connections to malicious domains. However, recent stealthy attacks hide malicious activities within seemingly legitimate connections to popular web services made by benign programs. Traditional DNS monitoring and signature-based detection techniques are ineffective against such attacks. To tackle this challenge, we present a new program-level approach that can effectively detect such stealthy attacks. Our method builds a fine-grained Program-DNS profile for each benign program that characterizes what should be the “expected” DNS behavior. We find that malware-injected processes have DNS activities which significantly deviate from the Program-DNS profile of the benign program. We then develop six novel features based on the Program-DNS profile, and evaluate the features on a dataset of over 130 million DNS requests collected from a real-world enterprise and 8 million requests from malware-samples executed in a sandbox environment. We compare our detection results with that of previously-proposed features and demonstrate that our new features successfully detect 190 malware-injected processes which fail to be detected by previously-proposed features. Overall, our study demonstrates that fine-grained Program-DNS profiles can provide meaningful and effective features in building detectors for attack campaigns that bypass existing detection systems.

Computer Networks fights with a continues issues with attackers and intruders. Attacks on distributed systems becoming more powerful and more frequent day by day. Intrusion detection methods are performing main role to detect intruders and attackers. To identify intrusion on computer or computer networks an intrusion detection system methods are used. Network Intrusion Detection System (NIDS) performs an prime role by presenting the network security. It gives a defense layer by monitoring the traffic on network for predefined distrustful activity or pattern. In this paper we have analyze and compare existing signature based and anomaly based algorithm with Openstack private cloud.

Domain Generation Algorithms (DGAs) are used by adversaries to establish Command and Control (C&C) server communications during cyber attacks. Blacklists of known/identified C&C domains are used as one of the defense mechanisms. However, static blacklists generated by signature-based approaches can neither keep up nor detect never-seen-before malicious domain names. To address this weakness, we applied a DGA-based malicious domain classifier using the Long Short-Term Memory (LSTM) method with a novel feature engineering technique. Our model's performance shows a greater accuracy compared to a previously reported model. Additionally, we propose a new adversarial machine learning-based method to generate never-before-seen malware-related domain families. We augment the training dataset with new samples to make the training of the models more effective in detecting never-before-seen malicious domain names. To protect blacklists of malicious domain names against adversarial access and modifications, we devise secure data containers to store and transfer blacklists.

In order to solve the problem of accurate positioning of mixed reality virtual scene in physical space, this paper, firstly, analyzes the positioning principle of mixed reality virtual scene. Secondly, based on the comparison among the three developer kits: ARToolKit, ARTag, and Vuforia and two image optimization algorithms: AHE and ACE, it makes sure to use Vuforia development tool to complete the signature-based tracking and registration task, and use ACE algorithm to optimize the signature-based image. It improves the efficiency, stability and accuracy of image recognition registration. Then the multi-target recognition and registration technology is used to realize the multi-location of virtual scene. Finally, Hololens glasses are used as the hardware carrier to verify the above method. The experimental results show that the above method not only realizes the precise location of MR virtual scene based on image recognition, but also ensures the absolute position of the virtual model in the real space, bringing users a more real virtual experience. Keywords-mixed reality, multi-person collaboration, virtual positioning, gesture interaction.

The rapid growth of IPv6 traffic makes security issues become more important. This paper proposes an IPv6 network security system that integrates signature-based Intrusion Detection Systems (IDS) and machine learning classification technologies to improve the accuracy of IPv6 denial-of-service (DoS) attacks detection. In addition, this paper has also enhanced IPv6 network security defense capabilities through software-defined networking (SDN) and network function virtualization (NFV) technologies. The experimental results prove that the detection and defense mechanisms proposed in this paper can effectively strengthen IPv6 network security.

There is very significant role of Virtualization in cloud computing. The physical hardware in the cloud computing reside with the host machine and the virtualization software runs on it. The virtualization allows virtual machines to exist. The host machine shares its physical components such as memory, storage, and processor ultimately to handle the needs of the virtual machines. If an attacker effectively compromises one VM, it could outbreak others on the same host on the network over long periods of time. This is an gradually more popular method for cross-virtual-machine attacks, since traffic between VMs cannot be examined by standard IDS/IPS software programs. As we know that the cloud environment is distributed in nature and hence more susceptible to various types of intrusion attacks which include installing malicious software and generating backdoors. In a cloud environment, where organizations have hosted important and critical data, the security of underlying technologies becomes critical. To alleviate the hazard to cloud environments, Intrusion Detection Systems (IDS) are a cover of defense. In this paper, we are proposing an innovative model for Intrusion Detection System for securing Host machines in cloud infrastructure. This proposed IDS has two important features: (1) signature based and (2) prompt alert system.