LLM Security Guard for Code
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Many developers rely on Large Language Models (LLMs) to facilitate software development. Nevertheless, these models have exhibited limited capabilities in the security domain. We introduce LLMSecGuard, a framework to offer enhanced code security through the synergy between static code analyzers and LLMs. LLMSecGuard is open source and aims to equip developers with code solutions that are more secure than the code initially generated by LLMs. This framework also has a benchmarking feature, aimed at providing insights into the evolving security attributes of these models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Of the thirteen agentic vulnerability-discovery studies coded in our corpus (eight single-agent and five multi-agent; Table 5; non-agentic baselines and feasibility/tool-only entries in the coded matrix are outside this count), only two report any quantitative evidence about findings that fail to reproduce under independent verification [123,124]; the remaining eleven report detection-style”
From Agentic AI and Large Language Models for Autonomous IoT Cybersecurity: A Systematic Survey, Taxonomy, and Research Roadmap (2026) · cites this paper as [124]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Large Language Models for Software Engineering: A Systematic Literature Review
Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., & Wang, H. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3695988 · Cited by 1,029
Large language models for software engineering: survey and open problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE) · doi:10.1109/icse-fose59343.2023.00008 · Cited by 650
Large Language Models for Software Engineering: Survey and Open Problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · arXiv · doi:10.48550/arxiv.2310.03533 · Cited by 523
Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions
Pearce, H., Ahmad, B., Tan, B., Dolan-Gavitt, B., & Karri, R. (2022) · 2022 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp46214.2022.9833571 · Cited by 476
Is GitHub’s Copilot as bad as humans at introducing vulnerabilities in code?
Asare, O., Nagappan, M., & Asokan, N. (2023) · Empirical Software Engineering · doi:10.1007/s10664-023-10380-1 · Cited by 128
Large Language Models for Software Engineering: A Systematic Literature Review
Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2308.10620 · Cited by 114
Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
Fu, Y., Liang, P., Tahir, A., Li, Z., Shahin, M., Yu, J., & Chen, J. (2023) · arXiv · doi:10.48550/arxiv.2310.02059 · Cited by 75
Ghafari, M., Gadient, P., & Nierstrasz, O. (2017) · IEEE International Working Conference on Source Code Analysis and Manipulation (SCAM) · doi:10.1109/scam.2017.24 · Cited by 72
Self-citationEvaluation of Static Vulnerability Detection Tools With Java Cryptographic API Benchmarks
Afrose, S., Xiao, Y., Rahaman, S., Miller, B. P., & Yao, D. D. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2022.3154717 · Cited by 54
An Investigation into Misuse of Java Security APIs by Large Language Models
Mousavi, Z., Islam, C., Moore, K., Abuadbba, A., & Babar, M. A. (2024) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3634737.3661134 · Cited by 42
Research works printed but not linked: 6
- Matteo Esposito, Valentina Falaschi, and Davide Falessi. 2024. An Extensive Comparison of Static Application Security Testing Tools. In 28th International Conference on Evaluation and Assessment in Software Engineering (Salerno, Italy) (EASE ’24).
- Hossein Hajipour, Keno Hassler, Thorsten Holz, Lea Schönherr, and Mario Fritz. 2024. CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models. In 2nd IEEE Conference on Secure and Trustworthy Machine Learning (Toronto, Canada) (SaTML ’24).
- M. Hazhirpasand, M. Ghafari, S. Kruger, E. Bodden, and O. Nierstrasz. 2019. The Impact of Developer Experience in Using Java Cryptography. In 2019 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement.
- Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin and Ting Liu. 2023. A Survey on Hallucination in Large Language Models: Principles Taxonomy Challenges and Open Questions. arxiv:2311.05232 [cs.CL] · arXiv
- Meta AI. Year of publication or last update. LLAMA: Language Model for Many Applications. https://ai.meta.com/llama/ Accessed on January 28, 2024.
- Ying Zhang, Md Mahir Asef Kabir, Ya Xiao, Danfeng Yao, and Na Meng. 2023. Automatic Detection of Java Cryptographic API Misuses: Are We There Yet?IEEE Transactions on Software Engineering 49, 1 (2023), 288–303.
Cited by
When LLMs meet cybersecurity: a systematic literature review
Zhang, J., Bu, H., Wen, H., Liu, Y., Fei, H., Xi, R., Li, L., Yang, Y., Zhu, H., & Meng, D. (2025) · Cybersecurity · doi:10.1186/s42400-025-00361-w · Cited by 383
“To ensure the generation of secure codes, LLM-SecGuard (Kavian et al. 2024) enhance code security through the synergy between static code analyzers and LLMs.”
Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models
Bruni, M., Gabrielli, F., Ghafari, M., & Kropp, M. (2025) · IEEE/ACM International Conference on AI Foundation Models and Software Engineering (FORGE) · doi:10.1109/forge66646.2025.00018 · Cited by 61
Self-citationLarge Language Models (LLMs) for Source Code Analysis: applications, models and datasetsPreprint
Jelodar, H., Meymani, M., & Razavi‐Far, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.17502 · Cited by 49
Correctness assessment of code generated by Large Language Models using internal representations
Bui, T.-D., Vu, T. T., Nguyen, T.-T., Nguyen, S., & Vo, H. D. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112570 · Cited by 48
Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection
Lin, B., Wang, S., Qin, Y., Chen, L., & Mao, X. (2025) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3719027.3765049 · Cited by 41
Chen, Z., & Jiang, L. (2025) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner64311.2025.00068 · Cited by 39
Exploring Research and Tools in AI Security: A Systematic Mapping Study
Narula, S., GhasemiGol, M., Carnerero-Cano, J., Minnich, A., Lupu, E., & Takabi, D. (2025) · IEEE Access · doi:10.1109/access.2025.3567195 · Cited by 31
Can LLMs Generate Higher Quality Code Than Humans? An Empirical Study
Jamil, M. T., Abid, S., & Shamail, S. (2025) · International Conference on Mining Software Repositories (MSR) · doi:10.1109/msr66628.2025.00081 · Cited by 21
Haque, M. A., Siddique, S., Rahman, M. M., Hasan, A. R., Das, L. R., Kamal, M., Shujaee, K. A., Gupta, K. D., & George, R. (2025) · International Conference on Intelligent Data Science Technologies and Applications (IDSTA) · doi:10.1109/idsta66210.2025.11202778 · Cited by 19
Firouzi, E., Ghafari, M., & Ebrahimi, M. (2024) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/3674805.3695408 · Cited by 16
Self-citationFirouzi, E., & Ghafari, M. (2026) · IEEE International Conference on Software Analysis, Evolution and Reengineering - Companion (SANER-C) · doi:10.1109/saner-c67878.2026.00042 · Cited by 13
Self-citationGenerative AI for Internet of Things Security: Challenges and OpportunitiesPreprint
Aung, Y. L., Christian, I., Ye, D., Ye, X., Chattopadhyay, S., & Zhou, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.08886 · Cited by 13
Inducing Vulnerable Code Generation in LLM Coding AssistantsPreprint
Zeng, B., Zhang, Q., Zhou, C., Go, G., Jiang, Y., & Shi, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.15867 · Cited by 11
Time to separate from StackOverflow and match with ChatGPT for encryption
Firouzi, E., & Ghafari, M. (2024) · Journal of Systems and Software · doi:10.1016/j.jss.2024.112135 · Cited by 10
Self-citationSaul, R., Wang, H., Sen, K., & Wagner, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.07313 · Cited by 10
Position: Vibe Coding Needs Vibe Reasoning: Improving Vibe Coding with Formal Verification
Mitchell, J., & Shaaban, Y. (2025) · Proceedings of the 1st ACM SIGPLAN International Workshop on Language Models and Programming Languages · doi:10.1145/3759425.3763390 · Cited by 8
Haque, A., Siddique, S., Rahman, M. M., Hasan, A. R., Laxmi, R., Das, Kamal, M., & Gupta, K. D. (2025) · arXiv (Cornell University) · doi:10.13140/rg.2.2.16796.60803 · Cited by 8
Vu, T. T., Bui, T.-D., Nguyen, T.-T., Nguyen, S., & Vo, H. D. (2026) · Journal of Systems and Software · doi:10.1016/j.jss.2026.112852 · Cited by 7
Can generative AI detect and fix real-world cryptographic misuses?
Firouzi, E., & Ghafari, M. (2025) · Journal of Systems and Software · doi:10.1016/j.jss.2025.112650 · Cited by 7
Self-citationCARE: Pre-Execution Command Verification for Shell-Executing LLM AgentsPreprint
Liu, Y., Zhang, W., Yang, Z., Zhang, Z., Feng, H., Wang, X., Qiu, P., Liu, Y., Póczos, B., & Hong, J. B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.21642 · Cited by 7
Think Broad, Act Narrow: CWE Identification with Multi-Agent Large Language ModelsPreprint
Sayagh, M., & Ghafari, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.01451 · Cited by 6
Self-citationCeran, O. (2025) · Gazi Journal of Engineering Sciences · doi:10.30855/gmbd.070525a13 · Cited by 5
Securing AI Code Generation Through Automated Pattern-Based Patching
Altiero, F., Cotroneo, D., Luca, R. D., & Liguori, P. (2025) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w65791.2025.00077 · Cited by 5
Nageshwaran, V., & Ezekiel, S. (2026) · Electronics · doi:10.3390/electronics15122740 · Cited by 4
“The cost is brittleness against unfamiliar protocols and the well-documented risk of hallucinated “vulnerabilities” that do not reproduce, both of which require human-in-the-loop verification [123,124].”
Nageshwaran, V., & Ezekiel, S. (2026) · doi:10.20944/preprints202606.0142.v1 · Cited by 4
Can Developers Rely on LLMs for Secure IaC Development?
Firouzi, E., Bhatt, S., & Ghafari, M. (2026) · IEEE International Conference on Software Analysis, Evolution and Reengineering - Companion (SANER-C) · doi:10.1109/saner-c67878.2026.00041 · Cited by 4
Self-citationFATS: A Prompt Injection Attack Utilizing Feign Security Agents with Deceptive Few-Shots Learning
Ren, Y., Chen, J., & Zhang, R. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7078-2_47 · Cited by 3
From Struggle to Simplicity with a Usable and Secure API for Encryption in Java
Firouzi, E., Mansuri, A., Ghafari, M., & Kaveh, M. (2024) · Proceedings of the ... ACM-IEEE International Symposium on Empirical Software Engineering and Measurement/International Symposium on Empirical Software Engineering and Measurement · doi:10.1145/3674805.3695405 · Cited by 3
Self-citationRepairing vulnerabilities without invisible hands. A differentiated replication study on LLMsPreprint
Camporese, M., & Massacci, F. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.20977 · Cited by 3
PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM PipelinesPreprint
Tapwal, R., Kumar, A., & Maple, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.10614 · Cited by 3
Technique for Identifying Texts Generated by Large Language Models
Fedotova, A., & Romanov, A. (2025) · Informatics and Automation · doi:10.15622/ia.24.5.7 · Cited by 2
From Data Leak to Secret Misses: the Impact of Data Leakage on Secret Detection Models
Soltaniani, F., & Ghafari, M. (2026) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner67736.2026.00078 · Cited by 2
Self-citationSecReEvalBench: A real-world scenario-based security resilience benchmark for large language models
Cui, H., & Liu, W. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109065 · Cited by 2
Feedback-based Automated Verification in Vibe Coding of CAS Adaptation Built on Constraint LogicPreprint
Töpfer, M., Plášil, F., Bureš, T., & Hnětynka, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.18607 · Cited by 2
Learning to detect hardcoded secrets
Soltaniani, F., & Ghafari, M. (2026) · Empirical Software Engineering · doi:10.1007/s10664-026-10929-w · Cited by 1
Self-citationScaling Down with Small Language Models: Vision, Application, Opportunities, and ChallengesPreprint
Khan, N. M., Bhattacharya, P., Xia, Y., Cai, J., Fang, K., Feng, H., & Gadekallu, T. R. (2026) · doi:10.36227/techrxiv.177004226.60393974/v1 · Cited by 1
SecEval: A Security Evaluation Dataset for Large Language Models
Cui, H., & Liu, W. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-6888-8_13
From Adoption to Deployment: A Qualitative Study on AI Integration in Software Development PracticePreprint
Tamanna, M., Lin, E., Gowda, S., Williams, L. A., & Wermke, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.16660
Helping Java developers reduce cryptographic API misuses
Schlichtig, M. (2026) · Habilitation Regulations of the Faculty of Mechanical Engineering (University of Paderborn) · doi:10.17619/unipb/1-2729
Kadam, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.38977
Position: Vibe Coding Needs Vibe Reasoning: Improving Vibe Coding with Formal Verification
Mitchell, J., & Shaaban, Y. (2025) · arXiv · Cited by 8
Metadata
- Authors
- Kavian, A., Pourhashem Kallehbasti, M. M., Kazemi, S., Firouzi, E., & Ghafari, M.
- Affiliations
- University of Science and Technology of Mazandaran (IR)
- University of Science and Technology of Mazandaran, Iran
- Clausthal University of Technology (DE)
- ORCID
- Venue
- Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering
- Publisher
- ACM
- Published
- 2024-06-18
- Pages
- 600-603
- OpenAlex
- W4396811058
- Cited by
- 20
- References
- 17
- Citations by year
- 2026: 7 · 2025: 12 · 2024: 1
- FWCI
- 7.62
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- International Conference on Evaluation and Assessment in Software Engineering (EASE) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Web Application Security Vulnerabilities
- Physical Sciences › Computer Science › Hardware and Architecture › Security and Verification in Computing
- Keywords
- large language models, code security, static code analysis, LLM-assisted software development, security vulnerabilities, secure code generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.