The use of learning-based techniques to achieve automated software vulnerability detection has been of longstanding interest within the software security domain. These data-driven solutions are enabled by large software vulnerability datasets used for training and benchmarking. However, we observe that the quality of the data powering these solutions is currently ill-considered, hindering the reliability and value of produced outcomes. Whilst awareness of software vulnerability data preparation challenges is growing, there has been little investigation into the potential negative impacts of software vulnerability data quality. For instance, we lack confirmation that vulnerability labels are correct or consistent. Our study seeks to address such shortcomings by inspecting five inherent data quality attributes for four state-of-the-art software vulnerability datasets and the subsequent impacts that issues can have on software vulnerability prediction models. Surprisingly, we found that all the analyzed datasets exhibit some data quality problems. In particular, we found 20–71% of vulnerability labels to be inaccurate in real-world datasets, and 17-99% of data points were duplicated. We observed that these issues could cause significant impacts on downstream models, either preventing effective model training or inflating benchmark performance. We advocate for the need to overcome such challenges. Our findings will enable better consideration and assessment of software vulnerability data quality in the future.

Software Vulnerability Prediction (SVP) is a data-driven technique for software quality assurance that has recently gained considerable attention in the Software Engineering research community. However, the difficulties of preparing Software Vulnerability (SV) related data is considered as the main barrier to industrial adoption of SVP approaches. Given the increasing, but dispersed, literature on this topic, it is needed and timely to systematically select, review, and synthesize the relevant peer-reviewed papers reporting the existing SV data preparation techniques and challenges. We have carried out a Systematic Literature Review (SLR) of SVP research in order to develop a systematized body of knowledge of the data preparation challenges, solutions, and the needed research. Our review of the 61 relevant papers has enabled us to develop a taxonomy of data preparation for SVP related challenges. We have analyzed the identified challenges and available solutions using the proposed taxonomy. Our analysis of the state of the art has enabled us identify the opportunities for future research. This review also provides a set of recommendations for researchers and practitioners of SVP approaches.

Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite the vulnerable class, the non-vulnerable modules are difficult to be verified and determined as truly exploit free given the limited manual efforts available. It results in uncertainty, introduces labeling noise in the datasets and affects conclusion validity. To address this issue, we propose novel learning methods that are robust to label impurities and can leverage the most from limited label data; noisy label learning. We investigate various noisy label learning methods applied to software vulnerability prediction. Specifically, we propose a two-stage learning method based on noise cleaning to identify and remediate the noisy samples, which improves AUC and recall of baselines by up to 8.9% and 23.4%, respectively. Moreover, we discuss several hurdles in terms of achieving a performance upper bound with semi-omniscient knowledge of the label noise. Overall, the experimental results show that learning from noisy labels can be effective for data-driven software and security analytics.

Software Vulnerability (SV) severity assessment is a vital task for informing SV remediation and triage. Ranking of SV severity scores is often used to advise prioritization of patching efforts. However, severity assessment is a difficult and subjective manual task that relies on expertise, knowledge, and standardized reporting schemes. Consequently, different data sources that perform independent analysis may provide conflicting severity rankings. Inconsistency across these data sources affects the reliability of severity assessment data, and can consequently impact SV prioritization and fixing. In this study, we investigate severity ranking inconsistencies over the SV reporting lifecycle. Our analysis helps characterize the nature of this problem, identify correlated factors, and determine the impacts of inconsistency on downstream tasks. Our findings observe that SV severity often lacks consideration or is underestimated during initial reporting, and such SVs consequently receive lower prioritization. We identify six potential attributes that are correlated to this misjudgment, and show that inconsistency in severity reporting schemes can severely degrade the performance of downstream severity prediction by up to 77%. Our findings help raise awareness of SV severity data inconsistencies and draw attention to this data quality problem. These insights can help developers better consider SV severity data sources, and improve the reliability of consequent SV prioritization. Furthermore, we encourage researchers to provide more attention to SV severity data selection.

Context: Developers usually seek solutions to addressing Security Vulnerabilities (SVs) on developer Question and Answer (Q&A) websites. However, there is still little known about these SV-specific discussions on different Q&A sites. Objective: We present a large-scale empirical study to understand developers’ SV discussions and how these discussions are being supported by Q&A sites. Method: We use topic modeling to uncover the topics of 71,329 curated SV posts from two large Q&A sites, namely Stack Overflow (SO) and Security StackExchange (SSE). We then analyze the popularity, difficulty, and level of expertise for each topic. We also perform a qualitative analysis to identify the types of solutions to SV-related questions. Results: We identify 13 main SV discussion topics. Many topics do not follow the distributions and trends in expert-based security sources, e.g., Common Weakness Enumeration (CWE) and Open Web Application Security Project (OWASP). We also discover that SV discussions attract more experts to answer than many other domains, but some difficult SV topics (e.g., Vulnerability Scanning Tools) still receive quite limited support from experts. Moreover, we identify seven key types of answers given to SV questions, in which SO often provides code and instructions, while SSE usually gives experience-based advice and explanations. Conclusion: Our findings provide support for researchers and practitioners to effectively acquire, share and leverage SV knowledge on Q&A sites.

Background: Static Application Security Testing (SAST) tools purport to assist developers in detecting security issues in source code. These tools typically use rule-based approaches to scan source code for security vulnerabilities. However, due to the significant shortcomings of these tools (i.e., high false positive rates), learning-based approaches for Software Vulnerability Prediction (SVP) are becoming a popular approach. Aims: Despite the similar objectives of these two approaches, their comparative value is unexplored. We provide an empirical analysis of SAST tools and SVP models, to identify their relative capabilities for source code security analysis. Method: We evaluate the detection and assessment performance of several common SAST tools and SVP models on a variety of vulnerability datasets. We further assess the viability and potential benefits of combining the two approaches. Results: SAST tools and SVP models provide similar detection capabilities, but SVP models exhibit better overall performance for both detection and assessment. Unification of the two approaches is difficult due to lacking synergies. Conclusions: Our study generates 12 main findings which provide insights into the capabilities and synergy of these two approaches. Through these observations we provide recommendations for use and improvement.

It is increasingly suggested to identify Software Vulnerabilities (SVs) in code commits to give early warnings about potential security risks. However, there is a lack of effort to assess vulnerability-contributing commits right after they are detected to provide timely information about the exploitability, impact and severity of SVs. Such information is important to plan and prioritize the mitigation for the identified SVs. We propose a novel Deep multi-task learning model, DeepCVA, to automate seven Commit-level Vulnerability Assessment tasks simultaneously based on Common Vulnerability Scoring System (CVSS) metrics. We conduct large-scale experiments on 1,229 vulnerability-contributing commits containing 542 different SVs in 246 real-world software projects to evaluate the effectiveness and efficiency of our model. We show that DeepCVA is the best-performing model with 38% to 59.8% higher Matthews Correlation Coefficient than many supervised and unsupervised baseline models. DeepCVA also requires 6.3 times less training and validation time than seven cumulative assessment models, leading to significantly less model maintenance cost as well. Over-all, DeepCVA presents the first effective and efficient solution to automatically assess SVs early in software systems.

Security is an increasing concern in software development. Developer Question and Answer (Q&A) websites provide a large amount of security discussion. Existing studies have used human-defined rules to mine security discussions, but these works still miss many posts, which may lead to an incomplete analysis of the security practices reported on Q&A websites. Traditional supervised Machine Learning methods can automate the mining process; however, the required negative (non-security) class is too expensive to obtain. We propose a novel learning framework, PUMiner, to automatically mine security posts from Q&A websites. PUMiner builds a context-aware embedding model to extract features of the posts, and then develops a two-stage PU model to identify security content using the labelled Positive and Un-labelled posts. We evaluate PUMiner on more than 17.2 million posts on Stack Overflow and 52,611 posts on Security StackExchange. We show that PUMiner is effective with the validation performance of at least 0.85 across all model configurations. Moreover, Matthews Correlation Coefficient (MCC) of PUMiner is 0.906, 0.534 and 0.084 points higher than one-class SVM, positive-similarity filtering, and one-stage PU models on unseen testing posts, respectively. PUMiner also performs well with an MCC of 0.745 for scenarios where string matching totally fails. Even when the ratio of the labelled positive posts to the un-labelled ones is only 1:100, PUMiner still achieves a strong MCC of 0.65, which is 160% better than fully-supervised learning. Using PUMiner, we provide the largest and up-to-date security content on Q&A websites for practitioners and researchers.