Distributed WSN Vulnerability Remediation System Based on Mobile-N Policy

Vulnerability is one of the root causes of network intrusion. An effective way to mitigate security threats is to discover and patch vulnerabilities before an attack. Traditional vulnerability detection methods rely on manual participation and incur a high false positive rate. The intelligent vulnerability detection methods suffer from the problems of long-term dependence, out of vocabulary, coarse detection granularity and lack of vulnerable samples. This paper proposes an automated and intelligent vulnerability detection method in source code based on the minimum intermediate representation learning. First, the sample in the form of source code is transformed into a minimum intermediate representation to exclude the irrelevant items and reduce the length of the dependency. Next, the intermediate representation is transformed into a real value vector through pre-training on an extended corpus, and the structure and semantic information are retained. Then, the vector is fed to three concatenated convolutional neural networks to obtain high-level features of vulnerability. Last, a classifier is trained using the learned features. To validate this vulnerability detection method, an experiment was performed. The empirical results confirmed that compared with the traditional methods and the state-of-the-art intelligent methods, our method has a better performance with fine granularity.

Due to the hostile environment, open communication and implementation vulnerability, ZigBee is vulnerable to various attacks. But there are few effective vulnerability detection methods. In this paper, we design the ZigBee Border Conditions Based Tester ZBCBT to detect vulnerabilities on MAC layer. It generates elaborated frames test cases transmitting to the target nodes. Based on ZBCBT, we present a ZigBee Border Conditions Algorithm ZBCA and a hostile test framework HTF for better test performance. Comparing with Random Testing RT or fuzz methods, ZBCA tests border values of every field in the frame to improve the efficiency. HTF is a unique framework that ZBCBT simulates an attacker is utilised for further tests. The experimental results, including one frame triggers the network crash, have proved ZBCBT's effectiveness. Thus, by using ZBCA and HTF, this novel vulnerability detection method is a significant add-on approach for ZigBee security.

Vulnerability detection through cross-modal feature enhancement and fusion

BinAIV: Semantic-enhanced vulnerability detection for Linux x86 binaries

The explosive growth of vulnerabilities poses a significant threat to the security of software systems. While various deep-learning-based vulnerability detection methods have emerged, they primarily rely on semantic features extracted from a single code representation structure, which limits their ability to detect vulnerabilities hidden deep within the code. To address this limitation, we propose S2FVD, short for Sequence and Structure Fusion-based Vulnerability Detector, which fuses vulnerability-indicative features learned from the multiple views of the code for more accurate vulnerability detection. Specifically, S2FVD employs either well-matched or carefully extended neural network models to extract vulnerability-indicative semantic features from the token sequence, attributed control flow graph (ACFG) and abstract syntax tree (AST) representations of a function, respectively. These features capture different perspectives of the code, which are then fused to enable S2FVD to accurately detect vulnerabilities that are well-hidden within a function. The experiments conducted on two large vulnerability datasets demonstrated the superior performance of S2FVD against state-of-the-art approaches, with its accuracy and F1 scores reaching 98.07% and 98.14% respectively in detecting the presence of vulnerabilities, and 97.93% and 97.94%, respectively, in pinpointing specific vulnerability types. Furthermore, with regard to the real-world dataset D2A, S2FVD achieved average performance gains of 6.86% and 14.84% in terms of accuracy and F1 metrics, respectively, over the state-of-the-art baselines. This ablation study also confirms the superiority of fusing the semantics implied in multiple distinct code views to further enhance vulnerability detection performance.

Code vulnerability detection is a crucial approach to ensuring software security, aiming to automatically identify potential security vulnerabilities in source code. However, existing static vulnerability detection methods often face challenges such as feature loss and an insufficient expressive power when extracting program features. To address these issues, in this paper, we propose a source code vulnerability detection method based on joint graph and multimodal feature fusion. Innovatively, we construct a joint graph that integrates multiple program dependencies and semantic edges to achieve more comprehensive feature extraction. Additionally, by combining Graph Attention Networks (GATs) with the Transformer architecture, both structural and sequential features of code snippets are captured, further enhancing the model’s expressive capabilities. Finally, we introduce pre-fusion and post-fusion strategies to fully integrate multimodal features, thereby improving the accuracy and performance of vulnerability detection. Experimental results on the SARD dataset demonstrate the method’s excellent performance in detecting various types of vulnerabilities, achieving an F1 score of 85.20% and an accuracy of 86.50%. On the Real-Vul real-world dataset, the method achieves an F1 score of 73.9% and an accuracy of 86.50%. The detection results exhibit remarkable stability, ensuring a reliable and consistent performance. Overall, the proposed method surpasses the performance of existing mainstream detection approaches.

The most severe problem in cross-programming languages is feature extraction due to different tokens in different programming languages. To solve this problem, we propose a cross-programming-language vulnerability detection method in this paper, IRC-CLVul, based on intermediate representation and combined features. Specifically, we first converted programs in different programming languages into a unified LLVM intermediate representation (LLVM-IR) to provide a classification basis for different programming languages. Afterwards, we extracted the code sequences and control flow graphs of the samples, used the semantic model to extract the program semantic information and graph structure information, and concatenated them into semantic vectors. Finally, we used Random Forest to learn the concatenated semantic vectors and obtained the classification results. We conducted experiments on 85,811 samples from the Juliet test suite in C, C++, and Java. The results show that our method improved the accuracy by 7% compared with the two baseline algorithms, and the F1 score showed a 12% increase.

At present, Cross Site Scripting (XSS) vulnerability exists in most web sites. The main reason is the lack of effective validation and filtering mechanisms for user input data from web request. This paper explores vulnerability detection method which based on taint dependence analysis and implements a prototype system for Java Web program. We treat all user input as tainted data, and track the flow of Web applications, then we judge whether it will trigger an attack or not. The taint dependent analysis algorithm mentioned in this paper is used to construct the taint dependency graph. Next the value representation method of the string tainted object based on finite state automata is discussed. Finally, we propose the vulnerability detection method for the program. The experiment result shows that the prototype system can detect reflection cross-site scripting vulnerability well in those programs which dont have effective treatment for the user input data.

Chapter 2 provides an overview of a literature study of the existing knowledge on energy consumption from the urban to the user scale, energy performance modelling methods, the energy performance gap, and insights to determinants of heating energy and electricity consumption. This review first helped to set up a reference point for the reasons to actual occupant behavior, how perception, lifestyle, norms, rules lead to various actions at home (Figure 1). Secondly, through this study, a framework for the relationship between occupant behavior and energy consumption was created (Figure 2), based on the determinants of behavior, i.e. occupant characteristics (educational, economic, social), dwelling characteristics (envelope, systems, lighting and appliances…). This literature study set the context and also the first steps of this research. The determinants found through this review (Table 2) gave input to the content and structure of the questions of the survey designed for the OTB dataset.

Models of energy consumption and performance are necessary to understand and identify system behavior, prior to designing advanced controls that can balance out performance and energy use. This paper considers the energy consumption and performance of servers running a relatively simple file-compression workload. We found that standard techniques for system identification do not produce acceptable models of energy consumption and performance, due to the intricate interplay between the discrete nature of software and the continuous nature of energy and performance. This motivated us to perform a detailed empirical study of the energy consumption and performance of this system with varying compression algorithms and compression levels, file types, persistent storage media, CPU DVFS levels, and disk I/O schedulers. Our results identify and illustrate factors that complicate the system's energy consumption and performance, including nonlinearity, instability, and multi-dimensionality. Our results provide a basis for future work on modeling energy consumption and performance to support principled design of controllable energy-aware systems.

A high-frequency surface-wave radar (HFSWR) ship tracking algorithm’s performance is significantly affected by the dynamics of ships, in which track fragmentation can be frequently observed. However, it is still unclear about in which scenarios the dynamics of ships sabotages the tracking performance. In this paper, an evolutionary-based vulnerability detection method is proposed to automatically collect scenarios of different ship motion dynamics that can cause quantitative failures in a HFSWR ship tracking algorithm. Firstly, a grammar-based scenario model which can describe multiple types of temporal relationships and generate autonomous motion of any number of ships with comparatively low-dimension data is proposed. Secondly, an encoding scheme of scenario is proposed and corresponding grammar-guided genetic programming (GGGP) algorithm is designed to evolve scenarios that can sabotages the tracking performance. Results show the effectiveness of this method in evolving and collecting scenarios that can cause more serious track fragmentation in the tracking results, with insights into the vulnerability of ship tracking algorithm provided.

The information interaction between the air-gapped internal network and the external Internet is only possible through authorized and strictly controlled methods. Attackers make use of the vulnerability to transmit information covertly by software-stimulated signals leakage, which vary from optical, acoustic to electromagnetic, so we need to find the vulnerabilities and protect them from malicious exploitation. In this paper, a simple and active method to detect these vulnerabilities is presented from an optical point of view, that is, the Light Emitting Diode (LED) status indicator and screen backlight are controlled to send information by frequency shift keying (FSK) or amplitude shift keying (ASK). Improved receiver is designed for acquisition of optical signals, and the vulnerability detection methods are unified for acoustic and electromagnetic vulnerability. The target signal is easily distinguished from the noise signal by the time-frequency domain characteristics, the hidden testing information is recovered by simple demodulation methods, and the mechanism of compromising emanation from digital signal is revealed. Several hidden features such as harmonics and intermodulation have been investigated, which can be used to detect optical, acoustic and electromagnetic vulnerability quickly.

Detecting software vulnerabilities has become increasingly challenging with the growing size and complexity of modern software. Traditional static and dynamic analysis methods often suffer from poor accuracy and reliance on expert knowledge. In recent years, deep learning has shown great promise in this domain due to its ability to automatically learn subtle features from software data. However, existing deep-learning-based methods face two main limitations: 1) difficulty in effectively processing long source code sequences, leading to suboptimal feature representation and 2) insufficient exploration and utilization of common vulnerability features, which hampers further performance improvements. To address these challenges, we propose DV-LVF, a novel deep-learning-based vulnerability detection method that combines program slicing with gated recurrent unit (GRU) embedding techniques to enhance feature representation. Additionally, we introduce a vulnerability dictionary (vulDict) that explicitly captures and leverages common vulnerability patterns to improve detection accuracy. Our evaluation demonstrates that DV-LVF outperforms state-of-the-art methods, achieving accuracies of 98.59% at the function level and 99.27% at the statement level. Notably, DV-LVF successfully identifies 11 previously unknown vulnerabilities across six open-source software projects, including GPAC, Vim, NanoMQ, PJSIP, Libmobi, and Radare2.

With the rapid development of the Internet, many things of people can be done online, and the Internet has been integrated into people's daily life. Web applications widely used in all walks of life are convenient for people to use, but also bring some security problems. Cross-Site Scripting(XSS) vulnerability detection method based on dynamic analysis is an effective XSS vulnerability detection method, which simulates real attack behavior to conduct penetration test on Web applications. However, there are still some problems such as low detection coverage, low detection efficiency and low detection accuracy. Based on this, this paper expounds the research status and background of XSS attack detection, puts forward the necessity of using machine learning algorithm for XSS attack detection, applies SVM algorithm to XSS detection, analyzes and extracts the features of XSS samples, selects radial basis kernel function for nonlinear SVM training, and verifies the generated detection model. It is found that the SVM model in this paper is also superior to the comparison algorithm in accuracy and false alarm rate.

Office buildings are usually characterized by low thermal inertia, which could cause underperformance in terms of energy consumption. Moreover, the use of large glazed façades in office buildings can cause thermal and visual discomfort due to high solar heat gains and excessive daylight transmitted into the office space. Phase Change Materials (PCMs) integrated into glazing have arisen as an innovative strategy to increase thermal inertia and improve office buildings’ energy performance and indoor comfort at a low cost. This paper aims to analyze the impact of PCM glazing on buildings’ energy performance and occupants’ thermal and visual comfort. The analysis is performed through a one-year real-scale experiment in two offices in Santiago, Chile, with an east-oriented façade and a window-to-wall ratio (WWR) of 56%. The results are analyzed on two timescales: seasonally and daily. Representative days in each season were selected to carry out the analysis. Regarding the energy consumption of the HVAC system, PCM glazing reduces energy consumption during summer and mid-seasons and significantly reduces the peak loads in summer. A meaningful improvement in thermal comfort is achieved due to the control of the mean radiant temperature for the whole year. Considering visual comfort, there is an improvement in the luminance distribution in winter and mid-season cold conditions.