Biblio

In software engineering, the aspect of addressing security requirements is considered to be of paramount importance. In most cases, however, security requirements for a system are considered as non-functional requirements (NFRs) and are addressed at the very end of the software development life cycle. The increasing number of security incidents in software systems around the world has made researchers and developers rethink and consider this issue at an earlier stage. An important and essential step towards this process is the elicitation of relevant security requirements. In a recent work, Imtiaz et al. proposed a framework for creating a mapping between existing requirements and the vulnerabilities associated with them. The idea is that, this mapping can be used by developers to predict potential vulnerabilities associated with new functional requirements and capture security requirements to avoid these vulnerabilities. However, to what extent, such existing vulnerability information can be useful in security requirements elicitation is still an open question. In this paper, we design a human subject study to answer this question. We also present the results of a pilot study and discuss their implications. Preliminary results show that existing vulnerability information can be a useful resource in eliciting security requirements and lays ground work for a full scale study.

Software vulnerabilities are closely monitored by the security community to timely address the security and privacy issues in software systems. Before a vulnerability is published by vulnerability management systems, it needs to be characterized to highlight its unique attributes, including affected software products and versions, to help security professionals prioritize their patches. Associating product names and versions with disclosed vulnerabilities may require a labor-intensive process that may delay their publication and fix, and thereby give attackers more time to exploit them. This work proposes a machine learning method to extract software product names and versions from unstructured CVE descriptions automatically. It uses Word2Vec and Char2Vec models to create context-aware features from CVE descriptions and uses these features to train a Named Entity Recognition (NER) model using bidirectional Long short-term memory (LSTM) networks. Based on the attributes of the product names and versions in previously published CVE descriptions, we created a set of Expert System (ES) rules to refine the predictions of the NER model and improve the performance of the developed method. Experiment results on real-life CVE examples indicate that using the trained NER model and the set of ES rules, software names and versions in unstructured CVE descriptions could be identified with F-Measure values above 0.95.

Software vulnerabilities threaten the security of computer system, and recently more and more loopholes have been discovered and disclosed. For the detected vulnerabilities, the relevant personnel will analyze the vulnerability characteristics, and combine the vulnerability scoring system to determine their severity level, so as to determine which vulnerabilities need to be dealt with first. In recent years, some characteristic description-based methods have been used to predict the severity level of vulnerability. However, the traditional text processing methods only grasp the superficial meaning of the text and ignore the important contextual information in the text. Therefore, this paper proposes an innovative method, called BERT-CNN, which combines the specific task layer of Bert with CNN to capture important contextual information in the text. First, we use Bert to process the vulnerability description and other information, including Access Gained, Attack Origin and Authentication Required, to generate the feature vectors. Then these feature vectors of vulnerabilities and their severity levels are input into a CNN network, and the parameters of the CNN are gotten. Next, the fine-tuned Bert and the trained CNN are used to predict the severity level of a vulnerability. The results show that our method outperforms the state-of-the-art method with 91.31% on F1-score.

The reuse of libraries in software development has become prevalent for improving development efficiency and software quality. However, security vulnerabilities of reused libraries propagated through software project dependency pose a severe security threat, but they have not yet been well studied. In this paper, we present the first large-scale empirical study of project dependencies with respect to security vulnerabilities. We developed PDGraph, an innovative approach for analyzing publicly known security vulnerabilities among numerous project dependencies, which provides a new perspective for assessing security risks in the wild. As a large-scale software collection in dependency, we find 337,415 projects and 1,385,338 dependency relations. In particular, PDGraph generates a project dependency graph, where each node is a project, and each edge indicates a dependency relationship. We conducted experiments to validate the efficacy of PDGraph and characterized its features for security analysis. We revealed that 1,014 projects have publicly disclosed vulnerabilities, and more than 67,806 projects are directly dependent on them. Among these, 42,441 projects still manifest 67,581 insecure dependency relationships, indicating that they are built on vulnerable versions of reused libraries even though their vulnerabilities are publicly known. During our eight-month observation period, only 1,266 insecure edges were fixed, and corresponding vulnerable libraries were updated to secure versions. Furthermore, we uncovered four underlying dependency risks that can significantly reduce the difficulty of compromising systems. We conducted a quantitative analysis of dependency risks on the PDGraph.

The relevance of data protection is related to the intensive informatization of various aspects of society and the need to prevent unauthorized access to them. World spending on ensuring information security (IS) for the current state: expenses in the field of IS today amount to \$81.7 billion. Expenditure forecast by 2020: about \$105 billion [1]. Information protection of military facilities is the most critical in the public sector, in the non-state - financial organizations is one of the leaders in spending on information protection. An example of the importance of IS research is the Trojan encoder WannaCry, which infected hundreds of thousands of computers around the world, attacks are recorded in more than 116 countries. The attack of the encoder of WannaCry (Wana Decryptor) happens through a vulnerability in service Server Message Block (protocol of network access to file systems) of Windows OS. Then, a rootkit (a set of malware) was installed on the infected system, using which the attackers launched an encryption program. Then each vulnerable computer could become infected with another infected device within one local network. Due to these attacks, about \$70,000 was lost (according to data from 18.05.2017) [2]. It is assumed in the presented work, that the software level of information protection is fundamentally insufficient to ensure the stable functioning of critical objects. This is due to the possible hardware implementation of undocumented instructions, discussed later. The complexity of computing systems and the degree of integration of their components are constantly growing. Therefore, monitoring the operation of the computer hardware is necessary to achieve the maximum degree of protection, in particular, data processing methods.

In transient distributed cloud computing environment, software is vulnerable to attack, which leads to software functional completeness, so it is necessary to carry out functional testing. In order to solve the problem of high overhead and high complexity of unsupervised test methods, an intelligent evaluation method for transient analysis software function testing based on active depth learning algorithm is proposed. Firstly, the active deep learning mathematical model of transient analysis software function test is constructed by using association rule mining method, and the correlation dimension characteristics of software function failure are analyzed. Then the reliability of the software is measured by the spectral density distribution method of software functional completeness. The intelligent evaluation model of transient analysis software function testing is established in the transient distributed cloud computing environment, and the function testing and reliability intelligent evaluation are realized. Finally, the performance of the transient analysis software is verified by the simulation experiment. The results show that the accuracy of the software functional integrity positioning is high and the intelligent evaluation of the transient analysis software function testing has a good self-adaptability by using this method to carry out the function test of the transient analysis software. It ensures the safe and reliable operation of the software.

The presence of software vulnerabilities is a serious threat to any software project. Exploiting them can compromise system availability, data integrity, and confidentiality. Unfortunately, many open source projects go for years with undetected ready-to-exploit critical vulnerabilities. In this study, we investigate the presence of software vulnerabilities in open source projects and the factors that influence this presence. We analyzed the top 100 open source PHP applications in GitHub using a static analysis vulnerability scanner to examine how common software vulnerabilities are. We also discussed which vulnerabilities are most present and what factors contribute to their presence. We found that 27% of these projects are insecure, with a median number of 3 vulnerabilities per vulnerable project. We found that the most common type is injection vulnerabilities, which made 58% of all detected vulnerabilities. Out of these, cross-site scripting (XSS) was the most common and made 43.5% of all vulnerabilities found. Statistical analysis revealed that project activities like branching, pulling, and committing have a moderate positive correlation with the number of vulnerabilities in the project. Other factors like project popularity, number of releases, and number of issues had almost no influence on the number of vulnerabilities. We recommend that open source project owners should set secure code development guidelines for their project members and establish secure code reviews as part of the project's development process.

The lack of knowledge about API correct usage rules is one of the main reasons that APIs are employed incorrectly by programmers, which in some cases lead to serious security vulnerabilities. However, finding a correct usage rule for an API is a time-consuming and error-prone task, particularly in the absence of an API documentation. Existing approaches to extract correct usage rules are mostly based on majority API usages, assuming the correct usage is prevalent. Although statistically extracting API correct usage rules achieves reasonable accuracy, it cannot work correctly in the absence of a fair amount of sample usages. We propose inferring API correct usage rules independent of the number of sample usages by leveraging an API tree structure. In an API tree, each node is an API, and each node's children are APIs called by the parent API. Starting from lower-level APIs, it is possible to infer the correct usage rules for them by utilizing the available correct usage rules of their children. We developed a tool based on our idea for inferring API correct usages rules hierarchically, and have applied it to the source code of Linux kernel v4.3 drivers and found 24 previously reported bugs.

A prioritized cyber defense remediation plan is critical for effective risk management in cyber-physical systems (CPS). The increased integration of Information Technology (IT)/Operational Technology (OT) in CPS has to lead to the need to identify the critical assets which, when affected, will impact resilience and safety. In this work, we propose a methodology for prioritized cyber risk remediation plan that balances operational resilience and economic loss (safety impacts) in CPS. We present a platform for modeling and analysis of the effect of cyber threats and random system faults on the safety of CPS that could lead to catastrophic damages. We propose to develop a data-driven attack graph and fault graph-based model to characterize the exploitability and impact of threats in CPS. We develop an operational impact assessment to quantify the damages. Finally, we propose the development of a strategic response decision capability that proposes optimal mitigation actions and policies that balances the trade-off between operational resilience (Tactical Risk) and Strategic Risk.

Software security is a major concern of the developers who intend to deliver a reliable software. Although there is research that focuses on vulnerability prediction and discovery, there is still a need for building security-specific metrics to measure software security and vulnerability-proneness quantitatively. The existing methods are either based on software metrics (defined on the physical characteristics of code; e.g. complexity or lines of code) which are not security-specific or some generic patterns known as nano-patterns (Java method-level traceable patterns that characterize a Java method or function). Other methods predict vulnerabilities using text mining approaches or graph algorithms which perform poorly in cross-project validation and fail to be a generalized prediction model for any system. In this paper, we envision to construct an automated framework that will assist developers to assess the security level of their code and guide them towards developing secure code. To accomplish this goal, we aim to refine and redefine the existing nano-patterns and software metrics to make them more security-centric so that they can be used for measuring the software security level of a source code (either file or function) with higher accuracy. In this paper, we present our visionary approach through a series of three consecutive studies where we (1) will study the challenges of the current software metrics and nano-patterns in vulnerability prediction, (2) will redefine and characterize the nano-patterns and software metrics so that they can capture security-specific properties of code and measure the security level quantitatively, and finally (3) will implement an automated framework for the developers to automatically extract the values of all the patterns and metrics for the given code segment and then flag the estimated security level as a feedback based on our research results. We accomplished some preliminary experiments and presented the results which indicate that our vision can be practically implemented and will have valuable implications in the community of software security.

Due to the abundance of security breaches we continue to see, the software development community is recently paying attention to a more proactive approach towards security. This includes predicting vulnerability before exploitation employing static code analysis and machine learning techniques. Such mechanisms, however, are designed to detect post-implementation vulnerabilities. As the root of a vulnerability can often be traced back to the requirement specification, and vulnerability discovered later in the development life cycle is more expensive to fix, we need additional preventive mechanisms capable of predicting vulnerability at a much earlier stage. In this paper, we propose a novel framework providing an automated support to predict vulnerabilities for a requirement as early as during requirement engineering. We further present a preliminary demonstration of our framework and the promising results we observe clearly indicate the value of this new research idea.

A significant milestone is reached when the field of software vulnerability research matures to a point warranting related security patterns represented by intelligent data. A substantial research material of empirical findings, distinctive taxonomy, theoretical models, and a set of novel or adapted detection methods justify a unifying research map. The growth interest in software vulnerability is evident from a large number of works done during the last several decades. This article briefly reviews research works in vulnerability enumeration, taxonomy, models and detection methods from the perspective of intelligent data processing and analysis. This article also draws the map which associated with specific characteristics and challenges of vulnerability research, such as vulnerability patterns representation and problem-solving strategies.

In this paper we conduct an empirical study with the purpose of identifying common software weaknesses of embedded devices used as part of industrial control systems in power grids. The data is gathered about the devices and software of 6 companies, ABB, General Electric, Schneider Electric, Schweitzer Engineering Laboratories, Siemens and Wind River. The study uses data from the manufacturersfi online databases, NVD, CWE and ICS CERT. We identified that the most common problems that were reported are related to the improper input validation, cryptographic issues, and programming errors.

Memory corruptions are still the most prominent venue to attack otherwise secure programs. In order to make exploitation of software bugs more difficult, defenders introduced a vast number of post corruption security mitigations, such as w⊕x memory, Stack Canaries, and Address Space Layout Randomization (ASLR), to only name a few. In the following, we describe the Wiedergänger1-Attack, a new attack vector that reliably allows to escalate unbounded array access vulnerabilities occurring in specifically allocated memory regions to full code execution on programs running on i386/x86\_64 Linux. Wiedergänger-attacks abuse determinism in Linux ASLR implementation combined with the fact that (even with protection mechanisms such as relro and glibc's pointer mangling enabled) there exist easy-to-hijack, writable (function) pointers in application memory. To discover such pointers, we use taint analysis and backwards slicing at the binary level and calculate an over-approximation of vulnerable instruction sequences. To show the relevance of Wiedergänger, we exploit one of the discovered instruction sequences to perform an attack on Debian 10 (Buster) by overwriting structures used by the dynamic loader (dl) that are present in any application with glibc and the dynamic loader as dependency. In order to show generality, we solely focus on data structures dispatched at program shutdown, as this is a point that arguably all applications eventually have to reach. This results in a reliable compromise that effectively bypasses all protection mechanisms deployed on x86\_64/i386 Linux to date. We believe Wiedergänger to be part of an under-researched type of control flow hijacking attacks targeting internal control structures of the dynamic loader for which we propose to use the terminology Loader Oriented Programming (LOP).

Software1 vulnerabilities are closely associated with information systems security, a major and critical field in today's technology. Vulnerabilities constitute a constant and increasing threat for various aspects of everyday life, especially for safety and economy, since the social impact from the problems that they cause is complicated and often unpredictable. Although there is an entire research branch in software engineering that deals with the identification and elimination of vulnerabilities, the growing complexity of software products and the variability of software production procedures are factors contributing to the ongoing occurrence of vulnerabilities, Hence, another area that is being developed in parallel focuses on the study and management of the vulnerabilities that have already been reported and registered in databases. The information contained in such databases includes, a textual description and a number of metrics related to vulnerabilities. The purpose of this paper is to investigate to what extend the assessment of the vulnerability severity can be inferred directly from the corresponding textual description, or in other words, to examine the informative power of the description with respect to the vulnerability severity. For this purpose, text mining techniques, i.e. text analysis and three different classification methods (decision trees, neural networks and support vector machines) were employed. The application of text mining to a sample of 70,678 vulnerabilities from a public data source shows that the description itself is a reliable and highly accurate source of information for vulnerability prioritization.

Vulnerability being the buzz word in the modern time is the most important jargon related to software and operating system. Since every now and then, software is developed some loopholes and incompleteness lie in the development phase, so there always remains a vulnerability of abruptness in it which can come into picture anytime. Detecting vulnerability is one thing and predicting its occurrence in the due course of time is another thing. If we get to know the vulnerability of any software in the due course of time then it acts as an active alarm for the developers to again develop sound and improvised software the second time. The proposal talks about the implementation of the idea using the artificial neural network, where different data sets are being given as input for being used for further analysis for successful results. As of now, there are models for studying the vulnerabilities in the software and networks, this paper proposal in addition to the current work, will throw light on the predictability of vulnerabilities over the due course of time.

Fuzz testing is a popular program testing technique. However, it is difficult to find hard-to-reach vulnerabilities that are nested with complex branches. In this paper, we propose semi-symbolic fuzz testing to discover hard-to-reach vulnerabilities. Our method groups inputs into high frequency and low frequency ones. Then symbolic execution is utilized to solve only uncovered branches to mitigate the path explosion problem. Especially, in order to play the advantages of fuzz testing, our method locates critical branch for each low frequency input and corrects the generated test cases to comfort the branch condition. We also implemented a prototype\textbackslashtextbarS2F, and the experimental results show that S2F can gain 17.70% coverage performance and discover more hard-to-reach vulnerabilities than other vulnerability detection tools for our benchmark.