mlsanityData to 14 Oct 2026

SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?

arXiv 2307.06616 ↗First posted 13 Jul 2023cs.CR cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

Software vulnerabilities can cause numerous problems, including crashes, data loss, and security breaches. These issues greatly compromise quality and can negatively impact the market adoption of software applications and systems. Traditional bug-fixing methods, such as static analysis, often produce false positives. While bounded model checking, a form of Formal Verification (FV), can provide more accurate outcomes compared to static analyzers, it demands substantial resources and significantly hinders developer productivity. Can Machine Learning (ML) achieve accuracy comparable to FV methods and be used in popular instant code completion frameworks in near real-time? In this paper, we introduce SecureFalcon, an innovative model architecture with only 121 million parameters derived from the Falcon-40B model and explicitly tailored for classifying software vulnerabilities. To achieve the best performance, we trained our model using two datasets, namely the FormAI dataset and the FalconVulnDB. The FalconVulnDB is a combination of recent public datasets, namely the SySeVR framework, Draper VDISC, Bigvul, Diversevul, SARD Juliet, and ReVeal datasets. These datasets contain the top 25 most dangerous software weaknesses, such as CWE-119, CWE-120, CWE-476, CWE-122, CWE-190, CWE-121, CWE-78, CWE-787, CWE-20, and CWE-762. SecureFalcon achieves 94% accuracy in binary classification and up to 92% in multiclassification, with instant CPU inference times. It outperforms existing models such as BERT, RoBERTa, CodeBERT, and traditional ML algorithms, promising to push the boundaries of software vulnerability detection and instant code completion frameworks.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 21 of its 67 references that are in the map. First posted on arXiv 13 Jul 2023.

Builds on

21 of 67 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2020Scaling Laws for Neural Language Modelscited by 6,586
  6. 2016Layer Normalizationcited by 5,669
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  9. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  10. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  11. 2020Calibrating Deep Neural Networks using Focal Losscited by 357
  12. 2019Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networkscited by 272
9 more
  1. 2020Deep Learning based Vulnerability Detection: Are We There Yet?cited by 144
  2. 2022Few-shot training LLMs for project-specific code-summarizationcited by 129
  3. 2023DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detectioncited by 102
  4. 2018SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilitiescited by 92
  5. 2022VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detectioncited by 51
  6. 2021Neural Transfer Learning for Repairing Security Vulnerabilities in C Codecited by 36
  7. 2023The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verificationcited by 34
  8. 2021Security Vulnerability Detection Using Deep Learning Natural Language Processingcited by 12
  9. 2022Explaining Software Bugs Leveraging Code Structures in Neural Machine Translationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 4.

13 papers.

Sort:

By area:

  1. 2025LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insightscited by 47
  2. 2024SECURE: Benchmarking Large Language Models for Cybersecuritycited by 14
  3. 2025Large Language Models for Security Operations Centers: A Comprehensive Surveycited by 9
  4. 2025Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overviewcited by 7
  5. 2025One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discoverycited by 6
  6. 2026From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detectioncited by 4
  7. 2025Revisiting Pre-trained Language Models for Vulnerability Detectioncited by 3
  8. 2025Advancing LLM-Based Security Automation with Customized Group Relative Policy Optimization for Zero-Touch Networkscited by 2
  9. 2026EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolutioncited by 2
  10. 2025ACSE-Eval: Can LLMs threat model real-world cloud infrastructure?cited by 1
  11. 2026Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools?cited by 1
  12. 2024DrLLM: Prompt-Enhanced Distributed Denial-of-Service Resistance Method with Large Language Modelscited by 0
1 more
  1. 2026A systematic literature Review for Transformer-based Software Vulnerability detectioncited by 0