mlsanityData to 7 Oct 2026

D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis

arXiv 2102.07995 ↗First posted 16 Feb 2021cs.SE cs.AI cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

Static analysis tools are widely used for vulnerability detection as they understand programs with complex behavior and millions of lines of code. Despite their popularity, static analysis tools are known to generate an excess of false positives. The recent ability of Machine Learning models to understand programming languages opens new possibilities when applied to static analysis. However, existing datasets to train models for vulnerability identification suffer from multiple limitations such as limited bug context, limited size, and synthetic and unrealistic source code. We propose D2A, a differential analysis based approach to label issues reported by static analysis tools. The D2A dataset is built by analyzing version pairs from multiple open source projects. From each project, we select bug fixing commits and we run static analysis on the versions before and after such commits. If some issues detected in a before-commit version disappear in the corresponding after-commit version, they are very likely to be real bugs that got fixed by the commit. We use D2A to generate a large labeled dataset to train models for vulnerability identification. We show that the dataset can be used to build a classifier to identify possible false alarms among the issues reported by static analysis, hence helping developers prioritize and investigate potential true positives first.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 7 of its 45 references that are in the map. First posted on arXiv 16 Feb 2021.

Builds on

7 of 45 references.

References · 7

  1. 2019Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networkscited by 266
  2. 2018Automated Vulnerability Detection in Source Code Using Deep Representation Learningcited by 114
  3. 2020Evolution of Semantic Similarity -- A Surveycited by 83
  4. 2020Exploring Software Naturalness through Neural Language Modelscited by 32
  5. 2017End-to-End Prediction of Buffer Overruns from Raw Source Code via Neural Memory Networkscited by 10
  6. 2020Learning to map source code to software vulnerability using code-as-a-graphcited by 9
  7. 2018Towards security defect prediction with AIcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 4; 2023: 6; 2024: 14; 2025: 13; 2026: 7.

48 papers.

Sort:

By area:

  1. 2021CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Taskscited by 199
  2. 2023DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detectioncited by 98
  3. 2021CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Softwarecited by 89
  4. 2022VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detectioncited by 51
  5. 2022An Empirical Study of Deep Learning Models for Vulnerability Detectioncited by 44
  6. 2025LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insightscited by 44
  7. 2025LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarkscited by 34
  8. 2023How Far Have We Gone in Vulnerability Detection Using Large Language Modelscited by 27
  9. 2021VELVET: a noVel Ensemble Learning approach to automatically locate VulnErable sTatementscited by 20
  10. 2022Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detectioncited by 18
  11. 2025From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEscited by 17
  12. 2022A Survey on Pretrained Language Models for Neural Code Intelligencecited by 13
36 more
  1. 2024Investigating Large Language Models for Code Vulnerability Detection: An Experimental Studycited by 11
  2. 2023Pitfalls in Language Models for Code Intelligence: A Taxonomy and Surveycited by 9
  3. 2024Are Latent Vulnerabilities Hidden Gems for Software Vulnerability Prediction? An Empirical Studycited by 9
  4. 2025Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generationcited by 9
  5. 2025Large Language Models for Security Operations Centers: A Comprehensive Surveycited by 9
  6. 2023When Less is Enough: Positive and Unlabeled Learning Model for Vulnerability Detectioncited by 8
  7. 2026ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Softwarecited by 8
  8. 2024Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detectioncited by 6
  9. 2024Revisiting the Performance of Deep Learning-Based Vulnerability Detection on Realistic Datasetscited by 6
  10. 2024Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?cited by 6
  11. 2025Combining Large Language Models with Static Analyzers for Code Review Generationcited by 6
  12. 2023An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graphcited by 5
  13. 2024Data Quality Issues in Vulnerability Detection Datasetscited by 5
  14. 2026Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filteringcited by 5
  15. 2024AI for DevSecOps: A Landscape and Future Opportunitiescited by 3
  16. 2024RealVul: Can We Detect Vulnerabilities in Web Applications with LLM?cited by 3
  17. 2025Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Qualitycited by 3
  18. 2026HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectorscited by 3
  19. 2025Data and Context Matter: Towards Generalizing AI-based Software Vulnerability Detectioncited by 2
  20. 2026SastBench: A Benchmark for Testing Agentic SAST Triagecited by 2
  21. 2021Data-Driven AI Model Signal-Awareness Enhancement and Introspectioncited by 1
  22. 2024ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Softwarecited by 1
  23. 2024PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Codecited by 1
  24. 2026Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Softwarecited by 1
  25. 2023ActiveClean: Generating Line-Level Vulnerability Data via Active Learningcited by 0
  26. 2024Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectorscited by 0
  27. 2024Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysiscited by 0
  28. 2024In-Context Code-Text Learning for Bimodal Software Engineeringcited by 0
  29. 2024Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Pointscited by 0
  30. 2025Today's Cat Is Tomorrow's Dog: Accounting for Time-Based Changes in the Labels of ML Vulnerability Detection Approachescited by 0
  31. 2025AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Datasetcited by 0
  32. 2025Weakly Supervised Vulnerability Localization via Multiple Instance Learningcited by 0
  33. 2025MulVuln: Enhancing Pre-trained LMs with Shared and Language-Specific Knowledge for Multilingual Vulnerability Detectioncited by 0
  34. 2025From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detectioncited by 0
  35. 2026CCCE: A Continuous Code Calibration Engine for Autonomous Enterprise Codebase Maintenance via Knowledge Graph Traversal and Adaptive Decision Gatingcited by 0
  36. 2026FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMscited by 0