Find research datasets worth reusing

Characterisation of Social Vulnerability to the environmental hazard of heat in Logroño, and the surrounding La Rioja region in Spain, derived from national census and EU Copernicus datasets.

This dataset includes all input information for indicators that were used to derive social vulnerability and the overall processed data of the social vulnerability index score for Logroño, and the surrounding La Rioja region, Spain. The input variables used in this dataset come from the national census data for Spain and EU Copernicus data. <div> The social vulnerability indicators used in these datasets are based on research including a review of existing literature and the interpretation of factors affecting social vulnerability. Interpretation of some indicators are contestable and open to debate. </div>

Characterisation of Social Vulnerability to the environmental hazard of flooding in Cork City and County, Ireland, derived from national census and EU Copernicus datasets.

This dataset includes all input information for indicators that were used to derive social vulnerability and the overall processed data of the social vulnerability index score for the region of Cork, Ireland. The input variables used in this dataset come from the national census data for Ireland and EU Copernicus data. <div> The social vulnerability indicators used in these datasets are based on research including a review of existing literature and the interpretation of factors affecting social vulnerability. Interpretation of some indicators are contestable and open to debate. </div>

Characterisation of Social Vulnerability to the environmental hazard of heat in Milan, derived from national census and EU Copernicus datasets

This dataset includes all input information for indicators that were used to derive social vulnerability and the overall processed data of the social vulnerability index score for the region of Milan, Italy. The input variables used in this dataset come from the national census data for Italy and EU Copernicus data. The social vulnerability indicators used in these datasets are based on research including a review of existing literature and the interpretation of factors affecting social vulnerability. Interpretation of some indicators are contestable and open to debate.

openmit-licenseApr 2024View details →

A collection of datasets for software vulnerability detection

This is a collection of datasets that are used for AI-based software vulnerability detection. All the datasets are in the .csv format and each row represents a sample. Each dataset includes a set of functions written in C and the target of each function is either 0 (non-vulnerable) or 1 (vulnerable). <ol> <li>data_C_Lin2017_test.csv: <ul> <li>Reference paper: <a href="https://dl.acm.org/doi/10.1145/3133956.3138840">Vulnerability Discovery with Function Representation Learning from Unlabeled Projects</a>, 2017.</li> <li>Data source on GitHub: <a href="https://github.com/DanielLin1986/function_representation_learning">https://github.com/DanielLin1986/function_representation_learning</a></li> <li>This dataset includes 44 vulnerable and 577 non-vulnerable functions from the LibPNG project.</li> </ul> </li> <li>data_C_LineVul_test.csv: <ul> <li>Reference paper: <a href="https://ieeexplore.ieee.org/document/9796256">LineVul: A Transformer-based Line-Level Vulnerability Prediction</a>, 2022.</li> <li>Data source on Hugging Face: <a href="https://huggingface.co/datasets/Partha117/LineVul_Test_Dataset">https://huggingface.co/datasets/Partha117/LineVul_Test_Dataset</a></li> <li>This dataset includes 1055 vulnerable and 17809 non-vulnerable functions.</li> </ul> </li> <li>data_C_PrimeVul_test.csv: <ul> <li>Reference paper: <a href="https://arxiv.org/abs/2403.18624">Vulnerability Detection with Code Language</a> <a href="https://arxiv.org/abs/2403.18624">Models: How Far Are We?</a> 2024.</li> <li>Data source on GitHub: <a href="https://github.com/DLVulDet/PrimeVul">https://github.com/DLVulDet/PrimeVul</a></li> <li>From the data source, the primevul_test.jsonl was used to created this dataset.</li> <li>This dataset includes 695 vulnerable and 25213 non-vulnerable functions.</li> </ul> </li> <li>data_C_Choi2017_test.csv: <ul> <li>Reference paper: <a href="https://www.ijcai.org/proceedings/2017/0214.pdf">End-to-End Prediction of Buffer Overruns from Raw Source Code</a> <a href="https://www.ijcai.org/proceedings/2017/0214.pdf">via Neural Memory Networks</a>, 2017.</li> <li>Data source on GitHub: <a href="https://github.com/mjc92/buffer_overrun_memory_networks">https://github.com/mjc92/buffer_overrun_memory_networks</a></li> <li>From GitHub, all the data in trainnig_100.txt, test_1_100.txt, test_2_100.txt,test_3_100.txt,test_4_100.txt, and corresponding _labels.txt files are combined to create this dataset.</li> <li>This dataset includes 7054 vulnerable and 6946 non-vulnerable functions.</li> </ul> </li> <li>data_C_Devign_test.csv: <ul> <li>Reference paper: <a href="https://proceedings.neurips.cc/paper_files/paper/2019/file/49265d2447bc3bbfe9e76306ce40a31f-Paper.pdf">Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks</a>, 2019</li> <li>Data source on Hugging Face: <a href="https://huggingface.co/datasets/claudios/code_x_glue_devign">https://huggingface.co/datasets/claudios/code_x_glue_devign</a></li> <li>From Hugging Face, all the data in train, validation, and test are combined to create this dataset.</li> <li>This dataset includes 12460 vulnerable and 14858 non-vulnerable functions.</li> </ul> </li> <li>data_C_Ours_{train,test}.csv: <ul> <li>This dataset is manually collected from projects on GitHub that have registered CVEs into NVD from 2002 to 2023. The 6,766 non-vulnerable code functions are extracted from the <a href="https://dl.acm.org/doi/10.1145/3607199.3607242">DiverseVul dataset</a> to increase the code diversity. </li> <li>This training set includes 5413 vulnerable and 5413 non-vulnerable functions.</li> <li>The test set includes 1353 vulnerable and 1353 non-vulnerable functions.</li> </ul> </li> </ol>

opencc-by-4.0Sep 2023View details →

Examining the Capacity of Text Mining and Software Metrics in Vulnerability Prediction [dataset]

This dataset contains the extension of a publicly available dataset that was published initially by Ferenc et al. in their paper: “Ferenc, R.; Hegedus, P.; Gyimesi, P.; Antal, G.; Bán, D.; Gyimóthy, T. Challenging machine learning algorithms in predicting vulnerable javascript functions. 2019 IEEE/ACM 7th InternationalWorkshop on Realizing Artificial Intelligence Synergies in Software Engineering (RAISE). IEEE, 2019, pp. 8–14.” The dataset contained software metrics for source code functions written in JavaScript (JS) programming language. Each function was labeled as vulnerable or clean. The authors gathered vulnerabilities from publicly available vulnerability databases. In our paper entitled: “Examining the Capacity of Text Mining and Software Metrics in Vulnerability Prediction” and cited as: “Kalouptsoglou I, Siavvas M, Kehagias D, Chatzigeorgiou A, Ampatzoglou A. Examining the Capacity of Text Mining and Software Metrics in Vulnerability Prediction. Entropy. 2022; 24(5):651. <a href="https://doi.org/10.3390/e24050651">https://doi.org/10.3390/e24050651</a>” , we presented an extended version of the dataset by extracting textual features for the labeled JS functions. In particular, we got the dataset provided by Ferenc et al. in CSV format and then we gathered all the GitHub URLs of the dataset's functions (i.e., methods). Using these URLs, we collected the source code of the corresponding JS files from GitHub. Subsequently, by utilizing the start and end line information for every function, we cut off the code of the functions. Each function was then tokenized to construct a list of tokens per function. To extract text features, we used a text mining technique called sequences of tokens. As a result, we created a repository with all methods' source code, the token sequences of each method, and their labels. To boost the generalizability of type-specific tokens, all comments were eliminated, as well as all integers and strings, which were replaced with two unique IDs. The dataset contains 12,106 JavaScript functions, from which 1,493 are considered vulnerable. This dataset was created and utilized during the Vulnerability Prediction Task of the Horizon2020 IoTAC Project as training and evaluation data for the construction of vulnerability prediction models. The dataset is provided in the csv format. Each row of the csv file has the following parts: <ul> <li>Label: Flag with values ‘1’ for vulnerable and ‘0’ for non-vulnerable methods</li> <li>Name: The name of the JavaScript method</li> <li>Longname: The longname of the JavaScript method</li> <li>Path: The path of the file of the method in the repository</li> <li>Full_repo_path: The GitHub URL of the file of the method</li> <li>TokenX: Each next row corresponds to each token included in the method</li> </ul>

zenodo48/100

Software vulnerability detection datasets - function/method level

This dataset is for software vulnerability detection and includes source code in eight programming languages (C, C++, Java, JavaScript, Go, PHP, Ruby, Python). All data is collected from GitHub.data{programming language}_vul.json: a set of vulnerable code samples in a certain programming language.data{programming language}_patch.json: a set of patching code samples in a certain programming language. Each source code sample includes the following 16 properties: index: index of code. If is_vulnerable==False, this index indicates that this code is a patch of the indexing vulnerable code.code: raw source code (may include comments).is_vulnerable: the code is vulnerable (True) or a patch (False).programming_language: programming language of the code.method_name: name of the method.file_name: name of the file where the source code is extracted.repo_url: url of the project repository.repo_owner: owner of the repository.committer: developer who pushed the commit.committer_date: date when the commit was pushed.commit_msg: the commit message.cwe_id: If is_vulnerable==True, the CWE id; otherwise None.cwe_name: If is_vulnerable==True, the name of corresponding CWE; otherwise None.cwe_description: If is_vulnerable==True, the description of corresponding CWE; otherwise None.cwe_url: If is_vulnerable==True, the url to obtain more details of corresponding CWE; otherwise None.cve_id: If is_vulnerable==True, the CVE id; otherwise None.

openmit-licenseSep 2024View details →

opencc-by-4.0Apr 2024View details →

Today's cat is tomorrow's dog: accounting for time-based changes in the labels of ML vulnerability detection approaches (Replication Package Part 3: OpenSSL dataset)

<h1>The Replication Package of</h1> <h1>"Today's cat is tomorrow's dog: accounting for time-based changes in the labels of ML vulnerability detection approaches"</h1> <h3>Part 3 (OPENSSL Dataset)</h3> <div> <div>This repository includes:</div> <ol> <li>Code.zip that contains the codes to replicate some parts of this study: a. 1_generate_datasets implements our methodology to generate the datasets. b. 2_run_models runs the ML models during the evaluation. c. 3_result_replication generates charts presented in the paper from the ML evaluation results.</li> <li>Datasets.zip that contain 2 folders: a. original datasets: 1 from <a href="https://github.com/CGCL-codes/VulDeePecker" target="_blank" rel="noopener">NVD Vuldeepecker</a> and 3 extracted from <a href="https://github.com/ZeoVan/MSR_20_Code_vulnerability_CSV_Dataset" target="_blank" rel="noopener">BigVul</a>. <div> <div>b. OPENSSL datasets: train, validation, test sets for each time of observation extracted using our methodology from <a href="https://github.com/ZeoVan/MSR_20_Code_vulnerability_CSV_Dataset" target="_blank" rel="noopener">BigVul</a> dataset for project openssl.</div> </div> </li> <li>Pretrained-models.zip that we generated during our evaluation (3 test results for each time point in the timeline [2013-2019]).</li> <li>Results.zip of our evaluation, the folder ALL contains the overall results and other folders are results by model.</li> </ol> UPDATED version 5 - added a GLOBAL_README.md which contains the 3 stages and how they are connected to each other - updated LineVul.ipynb: import AdamW from torch.optim instead of transformers - updated README.md in Code2Vec with the prerequisites of Java to run gradlew for astmine UPDATED version 6 - updated CodeBert.ipynb: import AdamW from torch.optim instead of transformers Documentations <ol> <li>INSTALL.pdf : how to install the codes</li> <li>README.pdf: readme file</li> <li>REQUIREMENTS.pdf: hardware and software requirements</li> <li>STATUS.pdf : status for artifact submission</li> <li>LICENSE.pdf: the license of this artifact</li> <li>PAPER.pdf: the camera-ready version of the paper</li> </ol> </div> <div> <div>Please refer to the following repositories for the other datasets and pre-trained models:</div> <div>- Part 1 NVD Vuldeeepecker : <a href="https://doi.org/10.5281/zenodo.8207883" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.8207883</a></div> - Part 2 LINUX : <a href="https://doi.org/10.5281/zenodo.10960662" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.10960662</a> <div>- Part 4 POPPLER : <a href="https://doi.org/10.5281/zenodo.14713143">https://doi.org/10.5281/zenodo.14713143</a></div> <div> </div> <div>This work was partly funded by the EU under the H2020 Program AssureMOSS (Grant n. 952647) and the Horizon Europe Program Sec4AI4Sec (Grant n. 101120393), by the Italian Ministry of University and Research (MUR) under the P.N.R.R. – NextGenerationEU grant n.\ PE00000014 (SERICS subproject COVERT), and by the Dutch Research Council (NWO) under the grant NWA.1215.18.006 (Theseus) and grant KIC1.VE01.20.004 (HEWSTI). </div> </div>

opencc-by-4.0Jan 2021View details →

Dataset: A Fly in the Ointment: An Empirical Study on the Characteristics of Ethereum Smart Contracts Code Weaknesses and Vulnerabilities

Dataset: A Fly in the Ointment: An Empirical Study on the Characteristics of Ethereum Smart Contracts Code Weaknesses and Vulnerabilities Majd Soud, Grischa Liebel, Mohammad Hamdaqa majd18@ru.is, grischal@ru.is, mhamdaqa@polymtl.ca. This Dataset includes the following:  1. "labeling.xml" files that represents the data for Categories of vulnerabilities in Smart Contracts for four data sources (i.e., Common Vulnerability and Exposure (CVE), Smart Contract Weakness Classification Registry (SWC), Stack Overflow, and GitHub) XML files structure: The XML files can be opened used any editor or any code editor (e.g. Visual Studio Code). 1. Each file has a root that is <Card_Table></Card_Table> which contains all the cards we labeled.  2. Each card is represented by the <Card></Card> and contains the following:             - The tag marked by <Tag> represents the keyword that was used to search and collect the card from StackOverflow.              - The URL marked by <URL> of the URL link which contains all the information of the labeled vulnerability.               - The other tages marked by <OtherTags> that shows all the tags used in the post on Stack Overflow.              - The expert labeling for the categories of vulnerabilities in each card is represented by  <CategoryExpertLabel>             - In more details, some records has the <SecondExpertCategoryLabel> that represents the second expert labeling for the categories of vulnerabilities.             - The <CategoryAgreement> used to calculate the inter-rater agreement between the two labelers.

opencc-by-4.0Sep 2024View details →

Vul4J+: A Dataset of Vulnerabilities for Automated Vulnerability Repair

<div> <div>Vul4J+ is a dataset of vulnerability fixes for automated vulnerability repair (AVR) in Java. Each entry of the dataset represents a vulnerability affecting an open-source Java project, having reference to the commit (revision) containing the code affected by the vulnerability and its version fixed by a human developer (the "left" and "right" parts of the commit). Each vulnerability is equipped with at least one "oracle" that shows the presence of the vulnerability, and that can be used to validate the correctness of patches generated by AVR tools. This *"oracle"* might have the form of a:</div> <div>- Vulnerability-witnessing test, i.e., a JUnit test case that fails on the vulnerable version of the code but passes on the patched version.</div> <div>- Warning/report raised by a vulnerability static analyzer, i.e., SpotBugs, that is presented in the vulnerable version of the code but not in the patched version.</div> <div>In essence, Vul4J+ is a cleaned up and extended version of Vul4J containing:</div> <div>- 106 known vulnerabilities with executable vulnerability-witnessing test cases in Docker containers and warnings (reports) from SpotBugs static analyzer (if found);</div> <div>- 79 come from the original Vul4J;</div> <div>- 27 result from the replication of the same protocol used in the original Vul4J;</div> <div>- 50 vulnerabilities stored in Docker containers with the warnings (reports) from SpotBugs static analyzer ;</div> <div>- 35 known vulnerabilities matched with vulnerability-witnessing test cases retrieved from projects in the wild.</div> <div>In total, Vul4J+ points to 191 vulnerabilities, each with at least one vulnerability oracle.</div> </div>

Dataset: Physical Vulnerability Database for Critical Infrastructure Hazard Risk Assessments

The Physical Vulnerability Database for Critical Infrastructure Hazard Risk Assements is a database that contains fragility and vulnerability curves that can be used to evaluate the expected or potential damages to infrastructure assets due to flooding, earthquakes, windstorms and landslides. The database consists of three Excel-spreadsheets: <ul> <li>Table_D1_Summary_CI_Vulnerability_Data: summary table with information on hazard, exposure, and vulnerability characteristics as well as a number of details regarding reliability and reference purposes.</li> <li>Table_D2_Hazard_Fragility_and_Vulnerability Curves: collection of fragility and vulnerability curves</li> <li>Table_D3_Costs: cost values that can be used in combination with the curves for the estimation of asset damages</li> </ul> Please consult the following publication for detailed information: Nirandjan, S., Koks, E. E., Ye, M., Pant, R., van Ginkel, K. C. H., Aerts, J. C. J. H., and Ward, P. J.: Review article: Physical Vulnerability Database for Critical Infrastructure Multi-Hazard Risk Assessments – A systematic review and data collection, Nat. Hazards Earth Syst. Sci. Discuss. [preprint], https://doi.org/10.5194/nhess-2023-208, in review, 2024.

opencc-by-4.0Oct 2021View details →

DATASETS and OUTCOMES - Assessment of intrinsic aquifer vulnerability at continental scale through a critical application of the DRASTIC method: the case of South America

A robust and comprehensive assessment of intrinsic aquifer vulnerability at continental scale map may represent an essential initial step towards a more sustainable land-use and water management. This repository contains the outcomes of an intrinsic aquifer vulnerability assessment of South America, performed by the DRASTIC method. The assets included in this repository are mainly raster maps (.tif, .geotif), created and georeferenced in QGIS (v3.16). Coordinate reference system (CRS) of the dataset is WGS84. Technical specifications of all graphical outcomes are stored in a dedicated file (README.txt).

openapache2.0Jul 2023View details →

AssureMOSS Vulnerability Statements Dataset (Tracer)

This dataset contains 307 vulnerability statements found with <a href="https://sap.github.io/project-kb/prospector/">Prospector</a>, an open-source repository mining tool developed by SAP Security Research and the <a href="https://assuremoss.eu">AssureMOSS consortium</a>. The vulnerabilities covered by this dataset are a subset of those that appear in the "depth" dataset at <a href="https://patch-tracer.github.io/">https://patch-tracer.github.io/</a>

opencc-by-4.0Dec 2018View details →

Dataset for "Architectural Security Weaknesses in Industrial Control Systems: An Empirical Study Based on Security Advisories' Vulnerability Reports"

Supplementary artifacts to "Architectural Security Weaknesses in Industrial Control Systems (ICS): An Empirical Study based on Disclosed Software Vulnerabilities" Published in the Proceedings from the 2019 IEEE International Conference on Software Architecture (ICSA) Package Contains: - Raw output showing Components, CAWEs, and CVEs per report - Frequency Data (# of reports) for those concerns - ICS Component - Term Dictionary  - HTML versions of reports studied in paper

opencc-by-4.0Oct 2023View details →

A dataset of seabird collision and displacement vulnerability factors relatively to marine wind farms in Portugal

The implementation of marine wind farms has grown considerably along northern European's northern Atlantic coasts (e.g. Baltic and North Sea) and a boom in these infrastructures is expected to take place along Europe's entire Atlantic and Mediterranean coasts. Accordingly, the Portuguese government has recently proposed priority sites for the construction of wind farms along the mainland coast. We used sensitivity mapping (Garthe & Hüppop, 2004) to assess which areas along the Portuguese coast are most sensitive for seabirds and to what extent the proposed sites for wind farm construction overlap with these areas.This dataset contains the base data to estimate a seabird Species Sensitivity Index (SSI) (following Bradbury et al., 2014, Certain et al., 2015), including scores for 11 species-specific ecological and behavioural factors related with seabird species' (i) vulnerability to collision with wind farms (4 factors), (ii) vulnerability to displacement due to disturbance by wind farms and associated maintenance (3 factors), and (iii) conservation status (4 factors). We reviewed the literature to mine and compile data on these factors for 34 seabird species that regularly occur along the Portuguese mainland coast. We updated factor scores, particularly for those factors that have been studied in greater detail in recent years using tracking technologies (Clairbaux & Jessopp, 2021). However, in many cases empirical data were unavailable and we used the scores presented in previous sensitivity mapping studies (Garthe & Hüppop, 2004; Bradbury et al., 2014; Certain et al., 2015; Wade et al., 2016; Serratosa & Allinson, 2022).

opencc-by-4.0Oct 2023View details →

Dataset for paper "Freihardt (2025): Environmental shocks and migration among a climate-vulnerable population in Bangladesh. Population and Environment. DOI 10.1007/s11111-025-00478-7"

This is the dataset underlying the paper:  Freihardt, J. (2025): Environmental shocks and migration among a climate-vulnerable population in Bangladesh. Population and Environment, 47, 6. DOI: 10.1007/s11111-025-00478-7.

opencc-by-4.0Jan 2022View details →

Project-KB based Vulnerability Method Dataset

This archive contains the vulnerability method dataset generated from project-KB. Every entry corresponds to a method and  contains metadata regarding the method and the label fixed or vulnerable. Additional details can be found in the readme file.

opencc-by-sa-4.0Mar 2022View details →

Code and Dataset for "Examining Zero-Shot Vulnerability Repair with Large Language Models"

Code and Dataset for "Examining Zero-Shot Vulnerability Repair with Large Language Models" The following Zenodo contains the resources associated with the S&P accepted paper ‘Examining Zero Shot Vulnerability Repair with Large Language Models’, https://arxiv.org/abs/2112.02125 In this resource, you can find the following.     - 'important_results' directory: This directory is for containing the final raw results as generated by the framework, including a global CSV of all generations and an HTML file containing all of the diffs generated for the 'high-confidence' real-world scenarios.         - final_results.csv             - This contains the final results of all generated software patches.             - Note the nomenclature differences with the manuscript tables. These are explained in the README in the framework.         - Original vs LLM-Generated Vulnerability Fixes.html             - This contains all of the diffs for the real-world patches versus the canonical developer-provided patches.     - 'framework' directory: This directory contains the complete archive of the code framework and all results at the time of the paper’s submission. It contains every language model prompt, suggestions, assembled repair patch and analysis data. It contains every script used for generation and analysis. It is a large archive, and within it contains an included README describing how to understand and use it.         - For convenience, we include a copy of the README external to the zipped archive.     - 'resources' directory:   This directory contains the resources used by our large associated tools, including:         - 'gpt2-csrc' subdirectory: Everything to do with the gpt2-csrc model, including the trained files, training scripts, and training data.         - 'ExtractFix' subdirectory: A docker image containing all ExtractFix scenarios, even those we did not use. Provided for interest (not required for usage).

opencc-by-4.0Aug 2022View details →

CVEfixes Dataset: Automatically Collected Vulnerabilities and Their Fixes from Open-Source Software

CVEfixes is a comprehensive vulnerability dataset that is automatically collected and curated from Common Vulnerabilities and Exposures (CVE) records in the public <a href="https://nvd.nist.gov/">U.S. National Vulnerability Database (NVD)</a>. The goal is to support data-driven security research based on source code and source code metrics related to fixes for CVEs in the NVD by providing detailed information at different interlinked levels of abstraction, such as the commit-, file-, and method level, as well as the repository- and CVE level. This release, v1.0.8, covers all published CVEs up to 23 July 2024. All open-source projects that were reported in CVE records in the NVD in this time frame _and_ had publicly available git repositories were fetched and considered for the construction of this vulnerability dataset. The dataset is organized as a relational database and covers 12107 vulnerability fixing commits in 4249 open source projects for a total of 11873 CVEs in 272 different Common Weakness Enumeration (CWE) types. The dataset includes the source code before and after changing 51342 files and 138974 functions. The collection took 48 hours with 4 workers (AMD EPYC Genoa-X 9684X). This repository includes the SQL dump of the dataset, as well as the JSON for the CVEs and XML of the CWEs at the time of collection. The complete process has been documented in the paper "CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software", which is published in the Proceedings of the 17th International Conference on Predictive Models and Data Analytics in Software Engineering (PROMISE '21). You will find a copy of the paper in the Doc folder.  Citation and Zenodo links Please cite this work by referring to the published paper: <ul> <li>Guru Bhandari, Amara Naseer, and Leon Moonen. 2021. CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software. In Proceedings of the 17th International Conference on Predictive Models and Data Analytics in Software Engineering (PROMISE '21). ACM, 10 pages. <a href="https://doi.org/10.1145/3475960.3475985">https://doi.org/10.1145/3475960.3475985</a></li> </ul> <pre><code>@inproceedings{bhandari2021:cvefixes, title = {{CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software}}, booktitle = {{Proceedings of the 17th International Conference on Predictive Models and Data Analytics in Software Engineering (PROMISE '21)}}, author = {Bhandari, Guru and Naseer, Amara and Moonen, Leon}, year = {2021}, pages = {10}, publisher = {{ACM}}, doi = {10.1145/3475960.3475985}, copyright = {Open Access}, isbn = {978-1-4503-8680-7}, language = {en} }</code></pre> The dataset has been released on Zenodo with DOI:<a href="https://doi.org/10.5281/zenodo.4476563">10.5281/zenodo.4476563</a>. The GitHub repository containing the code to automatically collect the dataset can be found at <a href="https://github.com/secureIT-project/CVEfixes">https://github.com/secureIT-project/CVEfixes</a>, released with DOI:<a href="https://doi.org/10.5281/zenodo.5111494">10.5281/zenodo.5111494</a>.

opencc-by-4.0Sep 2024View details →

Detection of Areas with Human Vulnerability Using Public Satellite Images and Deep Learning (Dataset)

<div> <h2>Overview</h2> <a href="https://github.com/fbvidal/HumanVulnerabilityDetectionDL#overview"></a></div> This repository contains the code and resources for the project titled "Detection of Areas with Human Vulnerability Using Public Satellite Images and Deep Learning". The goal of this project is to identify regions where individuals are living under precarious conditions and facing neglected basic needs, a situation often seen in Brazil. This concept is referred to as "human vulnerability" and is exemplified by families living in inadequate shelters or on the streets in both urban and rural areas. Focusing on the Federal District of Brazil as the research area, this project aims to develop two novel public datasets consisting of satellite images. The datasets contain imagery captured at 50m and 100m scales, covering regions of human vulnerability, traditional areas, and improperly disposed waste sites. The project also leverages these datasets for training deep learning models, including YOLOv7 and other state-of-the-art models, to perform image segmentation. A comparative analysis is conducted between the models using two training strategies: training from scratch with random weight initialization and fine-tuning using pre-trained weights through transfer learning. <div> <h3>Key Achievements</h3> <a href="https://github.com/fbvidal/HumanVulnerabilityDetectionDL#key-achievements"></a></div> <ul> <li>Two new satellite image datasets focusing on human vulnerability and improperly disposed waste sites, available in public domains.</li> <li>Comparison of image segmentation models, including YOLOv7 and Segmentation Models, with performance metrics.</li> <li>Best F1-scores: 0.55 for YOLOv7 and 0.64 for Segmentation Models.</li> </ul> This repository provides the code, models, and data pipelines used for training, evaluation, and performance comparison of these deep learning models. <div> <h2>Citation (Bibtex)</h2> <a href="https://github.com/fbvidal/HumanVulnerabilityDetectionDL?tab=readme-ov-file#citation-bibtex"></a></div> <pre><code>@TECHREPORT {TechReport-Julia-Laura-HumanVulnerability-2024, author = "Julia Passos Pontes, Laura Maciel Neves Franco, Flavio De Barros Vidal", title = "Detecção de Áreas com Atividades de Vulnerabilidade Humana utilizando Imagens Públicas de Satélites e Aprendizagem Profunda", institution = "University of Brasilia", year = "2024", type = "Undergraduate Thesis", address = "Computer Science Department - University of Brasilia - Asa Norte - Brasilia - DF, Brazil", month = "aug", note = "People living in precarious conditions and with their basic needs neglected is an unfortunate reality in Brazil. This scenario will be approached in this work according to the concept of \"human vulnerability\" and can be exemplified through families who live in inadequate shelters, without basic structures and on the streets of urban or rural centers. Therefore, assuming the Federal District as the research scope, this project proposes to develop two new databases to be made available publicly, considering the map scales of 50m and 100m, and composed by satellite images of human vulnerability areas, regions treated as traditional and waste disposed inadequately. Furthermore, using these image bases, trainings were done with the YOLOv7 model and other deep learning models for image segmentation. By adopting an exploratory approach, this work compares the results of different image segmentation models and training strategies, using random weight initialization (from scratch) and pre-trained weights (transfer learning). Thus, the present work was able to reach maximum F1 score values of 0.55 for YOLOv7 and 0.64 for other segmentation models." } </code></pre> <div> </div> <div> <h2>License</h2> <a href="https://github.com/fbvidal/HumanVulnerabilityDetectionDL?tab=readme-ov-file#license"></a></div> This project is licensed under the MIT License - see the LICENSE file for details.