{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/vulnerability-detection","name":"Vulnerability Detection","slug":"vulnerability-detection","description_markdown":"Vulnerability detection plays a crucial role in safeguarding against these threats by identifying weaknesses and potential entry points that malicious actors could exploit. Through advanced scanning techniques and penetration testing, vulnerability detection tools meticulously analyze web applications and websites for vulnerabilities such as SQL injection, cross-site scripting (XSS), and insecure authentication mechanisms.\r\n\r\nBy proactively identifying and addressing vulnerabilities, organizations can strengthen their online security posture and mitigate the risk of data breaches, financial loss, and reputational damage. Additionally, vulnerability detection empowers businesses to stay compliant with industry regulations and standards, demonstrating their commitment to safeguarding sensitive information and maintaining the trust of their customers. With the evolving threat landscape and increasingly sophisticated attack vectors, investing in robust vulnerability detection measures is paramount for staying one step ahead of cyber threats and ensuring the resilience of web-based platforms and services.","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":216,"papers_with_code":72,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/vulnerability-detection-on-vulscriber","slug":"vulnerability-detection-on-vulscriber","dataset":"VulScribeR","dataset_url":"/dataset/vulscriber","rows_in_archive":6,"metrics":["F1 Score"],"first_row_in_archive_order":{"model":"Reveal Model - Tested on Reveal (Training on Devign + VulScribeR 20K + Extra Cleans)","paper_title":"VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs","paper_url":"/paper/exploring-rag-based-vulnerability","paper_date":"2024-08-07","arxiv_id":"2408.04125","code_links":[{"title":"VulScribeR/VulScribeR","url":"https://github.com/VulScribeR/VulScribeR"}],"syntology":null}},{"leaderboard":"/sota/vulnerability-detection-on-vulnerability-java","slug":"vulnerability-detection-on-vulnerability-java","dataset":"Vulnerability Java Dataset","dataset_url":"/dataset/vulnerability-java-dataset","rows_in_archive":2,"metrics":["AUC","F1"],"first_row_in_archive_order":{"model":"WizardCoder","paper_title":"Finetuning Large Language Models for Vulnerability Detection","paper_url":"/paper/finetuning-large-language-models-for","paper_date":"2024-01-30","arxiv_id":"2401.17010","code_links":[{"title":"rmusab/vul-llm-finetune","url":"https://github.com/rmusab/vul-llm-finetune"}],"syntology":null}}],"datasets":[{"url":"/dataset/cvefixes","name":"CVEfixes","full_name":"","num_papers_in_archive":38},{"url":"/dataset/castle-benchmark","name":"CASTLE Benchmark","full_name":"CASTLE Benchmark C@250","num_papers_in_archive":1},{"url":"/dataset/iotvulcode","name":"IoTvulCode","full_name":"","num_papers_in_archive":1},{"url":"/dataset/realvul","name":"RealVul","full_name":"RealVul-Vulnerability Dataset following realistic settings","num_papers_in_archive":1},{"url":"/dataset/vulnerability-java-dataset","name":"Vulnerability Java Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vulnerable-verified-smart-contracts","name":"Vulnerable Verified Smart Contracts","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vulscriber","name":"VulScribeR","full_name":"VulScriber: 22K+ unfiltered vul samples generated with ChatGPT via Injection","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":216,"of_with_code":72,"tagged_in_all":216,"counts":{"archive_papers_tagged":216,"with_a_code_link":72,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":216,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/nyu-ctf-dataset-a-scalable-open-source","slug":"nyu-ctf-dataset-a-scalable-open-source","title":"NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security","date":"2024-06-08","arxiv_id":"2406.05590","repositories_listed":5,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nyu-ctf-dataset-a-scalable-open-source#ran","syntology_url":"https://syntology.ai/paper/2406.05590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05590"}},"official":{"repos":["nyu-llm-ctf/llm_ctf_automation","nyu-llm-ctf/llm_ctf_database","nyu-llm-ctf/nyu_ctf_bench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vuldeepecker-a-deep-learning-based-system-for","slug":"vuldeepecker-a-deep-learning-based-system-for","title":"VulDeePecker: A Deep Learning-Based System for Vulnerability Detection","date":"2018-01-05","arxiv_id":"1801.01681","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/vuldeepecker-a-deep-learning-based-system-for#ran","syntology_url":"https://syntology.ai/paper/1801.01681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01681"}},"official":{"repos":["CGCL-codes/VulDeePecker"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/sysevr-a-framework-for-using-deep-learning-to","slug":"sysevr-a-framework-for-using-deep-learning-to","title":"SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities","date":"2018-07-18","arxiv_id":"1807.06756","repositories_listed":4,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sysevr-a-framework-for-using-deep-learning-to#ran","syntology_url":"https://syntology.ai/paper/1807.06756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.06756"}},"official":{"repos":["SySeVR/SySeVR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/limits-of-machine-learning-for-automatic","slug":"limits-of-machine-learning-for-automatic","title":"Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection","date":"2023-06-28","arxiv_id":"2306.17193","repositories_listed":3,"syntology":null},{"url":"/paper/safe-self-attentive-function-embeddings-for","slug":"safe-self-attentive-function-embeddings-for","title":"SAFE: Self-Attentive Function Embeddings for Binary Similarity","date":"2018-11-13","arxiv_id":"1811.05296","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-self-attentive-function-embeddings-for#ran","syntology_url":"https://syntology.ai/paper/1811.05296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.05296"}},"official":null}},{"url":"/paper/deep-smart-contract-intent-detection","slug":"deep-smart-contract-intent-detection","title":"Deep Smart Contract Intent Detection","date":"2022-11-19","arxiv_id":"2211.10724","repositories_listed":2,"syntology":null},{"url":"/paper/trex-learning-execution-semantics-from-micro","slug":"trex-learning-execution-semantics-from-micro","title":"Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity","date":"2020-12-16","arxiv_id":"2012.08680","repositories_listed":2,"syntology":null},{"url":"/paper/automated-vulnerability-detection-in-source","slug":"automated-vulnerability-detection-in-source","title":"Automated Vulnerability Detection in Source Code Using Deep Representation Learning","date":"2018-07-11","arxiv_id":"1807.04320","repositories_listed":2,"syntology":null},{"url":"/paper/boosting-vulnerability-detection-of-llms-via","slug":"boosting-vulnerability-detection-of-llms-via","title":"Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data","date":"2025-06-09","arxiv_id":"2506.07390","repositories_listed":1,"syntology":null},{"url":"/paper/sv-trusteval-c-evaluating-structure-and","slug":"sv-trusteval-c-evaluating-structure-and","title":"SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis","date":"2025-05-27","arxiv_id":"2505.20630","repositories_listed":1,"syntology":null},{"url":"/paper/craken-cybersecurity-llm-agent-with-knowledge","slug":"craken-cybersecurity-llm-agent-with-knowledge","title":"CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution","date":"2025-05-21","arxiv_id":"2505.17107","repositories_listed":1,"syntology":null},{"url":"/paper/are-sparse-autoencoders-useful-for-java","slug":"are-sparse-autoencoders-useful-for-java","title":"Are Sparse Autoencoders Useful for Java Function Bug Detection?","date":"2025-05-15","arxiv_id":"2505.10375","repositories_listed":1,"syntology":null},{"url":"/paper/can-you-really-trust-code-copilots-evaluating","slug":"can-you-really-trust-code-copilots-evaluating","title":"Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective","date":"2025-05-15","arxiv_id":"2505.10494","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-large-language-models-with-faster","slug":"enhancing-large-language-models-with-faster","title":"Enhancing Large Language Models with Faster Code Preprocessing for Vulnerability Detection","date":"2025-05-08","arxiv_id":"2505.05600","repositories_listed":1,"syntology":null},{"url":"/paper/program-semantic-inequivalence-game-with","slug":"program-semantic-inequivalence-game-with","title":"Program Semantic Inequivalence Game with Large Language Models","date":"2025-05-02","arxiv_id":"2505.03818","repositories_listed":1,"syntology":null},{"url":"/paper/the-hitchhiker-s-guide-to-program-analysis","slug":"the-hitchhiker-s-guide-to-program-analysis","title":"The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs","date":"2025-04-16","arxiv_id":"2504.11711","repositories_listed":1,"syntology":null},{"url":"/paper/r2vul-learning-to-reason-about-software","slug":"r2vul-learning-to-reason-about-software","title":"R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation","date":"2025-04-07","arxiv_id":"2504.04699","repositories_listed":1,"syntology":null},{"url":"/paper/responsible-development-of-offensive-ai","slug":"responsible-development-of-offensive-ai","title":"Responsible Development of Offensive AI","date":"2025-04-03","arxiv_id":"2504.02701","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-with-llms-for-zero-shot","slug":"reasoning-with-llms-for-zero-shot","title":"Reasoning with LLMs for Zero-Shot Vulnerability Detection","date":"2025-03-22","arxiv_id":"2503.17885","repositories_listed":1,"syntology":null},{"url":"/paper/castle-benchmarking-dataset-for-static-code","slug":"castle-benchmarking-dataset-for-static-code","title":"CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection","date":"2025-03-12","arxiv_id":"2503.09433","repositories_listed":1,"syntology":null},{"url":"/paper/mtvhunter-smart-contracts-vulnerability","slug":"mtvhunter-smart-contracts-vulnerability","title":"MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation","date":"2025-02-24","arxiv_id":"2502.16955","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-select-pre-trained-code-models-for","slug":"how-to-select-pre-trained-code-models-for","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","date":"2025-01-07","arxiv_id":"2501.03783","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-large-language-models-for-code","slug":"investigating-large-language-models-for-code","title":"Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study","date":"2024-12-24","arxiv_id":"2412.18260","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-generative-ai-to-enhance-automated","slug":"leveraging-generative-ai-to-enhance-automated","title":"Leveraging Generative AI to Enhance Automated Vulnerability Scoring","date":"2024-12-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cryptoformaleval-integrating-llms-and-formal","slug":"cryptoformaleval-integrating-llms-and-formal","title":"CryptoFormalEval: Integrating LLMs and Formal Verification for Automated Cryptographic Protocol Vulnerability Detection","date":"2024-11-20","arxiv_id":"2411.13627","repositories_listed":1,"syntology":null},{"url":"/paper/is-function-similarity-over-engineered","slug":"is-function-similarity-over-engineered","title":"Is Function Similarity Over-Engineered? Building a Benchmark","date":"2024-10-30","arxiv_id":"2410.22677","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/is-function-similarity-over-engineered#ran","syntology_url":"https://syntology.ai/paper/2410.22677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22677"}},"official":{"repos":["FutureComputing4AI/Reverse-Engineering-Function-Search"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vulnerability-detection-via-topological","slug":"vulnerability-detection-via-topological","title":"Vulnerability Detection via Topological Analysis of Attention Maps","date":"2024-10-04","arxiv_id":"2410.03470","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-rag-based-vulnerability","slug":"exploring-rag-based-vulnerability","title":"VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs","date":"2024-08-07","arxiv_id":"2408.04125","repositories_listed":1,"syntology":null},{"url":"/paper/eatvul-chatgpt-based-evasion-attack-against","slug":"eatvul-chatgpt-based-evasion-attack-against","title":"EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection","date":"2024-07-27","arxiv_id":"2407.19216","repositories_listed":1,"syntology":null},{"url":"/paper/eyeballvul-a-future-proof-benchmark-for","slug":"eyeballvul-a-future-proof-benchmark-for","title":"eyeballvul: a future-proof benchmark for vulnerability detection in the wild","date":"2024-07-11","arxiv_id":"2407.08708","repositories_listed":1,"syntology":null},{"url":"/paper/morefixes-a-large-scale-dataset-of-cve-fix","slug":"morefixes-a-large-scale-dataset-of-cve-fix","title":"MoreFixes: A Large-Scale Dataset of CVE Fix Commits Mined through Enhanced Repository Discovery","date":"2024-07-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dart-deep-adversarial-automated-red-teaming","slug":"dart-deep-adversarial-automated-red-teaming","title":"Automated Progressive Red Teaming","date":"2024-07-04","arxiv_id":"2407.03876","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-the-performance-of-deep-learning","slug":"revisiting-the-performance-of-deep-learning","title":"Revisiting the Performance of Deep Learning-Based Vulnerability Detection on Realistic Datasets","date":"2024-07-03","arxiv_id":"2407.03093","repositories_listed":1,"syntology":null},{"url":"/paper/defining-and-detecting-vulnerability-in-human","slug":"defining-and-detecting-vulnerability-in-human","title":"Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation","date":"2024-06-12","arxiv_id":"2406.07935","repositories_listed":1,"syntology":null},{"url":"/paper/vuldetectbench-evaluating-the-deep-capability","slug":"vuldetectbench-evaluating-the-deep-capability","title":"VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models","date":"2024-06-11","arxiv_id":"2406.07595","repositories_listed":1,"syntology":null},{"url":"/paper/an-llm-assisted-easy-to-trigger-backdoor","slug":"an-llm-assisted-easy-to-trigger-backdoor","title":"An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection","date":"2024-06-10","arxiv_id":"2406.06822","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-llm-assisted-easy-to-trigger-backdoor#ran","syntology_url":"https://syntology.ai/paper/2406.06822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06822"}},"official":{"repos":["datasec-lab/codebreaker"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalization-enhanced-code-vulnerability","slug":"generalization-enhanced-code-vulnerability","title":"Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning","date":"2024-06-06","arxiv_id":"2406.03718","repositories_listed":1,"syntology":null},{"url":"/paper/iotvulcode-ai-enabled-vulnerability-detection","slug":"iotvulcode-ai-enabled-vulnerability-detection","title":"IoTvulCode: AI-enabled vulnerability detection in software products designed for IoT applications","date":"2024-05-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-cyber-security-a","slug":"large-language-models-for-cyber-security-a","title":"Large Language Models for Cyber Security: A Systematic Literature Review","date":"2024-05-08","arxiv_id":"2405.04760","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-for-cyber-security-a#ran","syntology_url":"https://syntology.ai/paper/2405.04760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04760"}},"official":{"repos":["hiyouga/llama-efficient-tuning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/graph-neural-networks-for-vulnerability","slug":"graph-neural-networks-for-vulnerability","title":"Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation","date":"2024-04-24","arxiv_id":"2404.15687","repositories_listed":1,"syntology":null},{"url":"/paper/machine-learning-techniques-for-python-source","slug":"machine-learning-techniques-for-python-source","title":"Machine Learning Techniques for Python Source Code Vulnerability Detection","date":"2024-04-15","arxiv_id":"2404.09537","repositories_listed":1,"syntology":null},{"url":"/paper/vulnerability-detection-with-code-language","slug":"vulnerability-detection-with-code-language","title":"Vulnerability Detection with Code Language Models: How Far Are We?","date":"2024-03-27","arxiv_id":"2403.18624","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vulnerability-detection-with-code-language#ran","syntology_url":"https://syntology.ai/paper/2403.18624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18624"}},"official":{"repos":["dlvuldet/primevul"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-role-consensus-through-llms-discussions","slug":"multi-role-consensus-through-llms-discussions","title":"Multi-role Consensus through LLMs Discussions for Vulnerability Detection","date":"2024-03-21","arxiv_id":"2403.14274","repositories_listed":1,"syntology":null},{"url":"/paper/finetuning-large-language-models-for","slug":"finetuning-large-language-models-for","title":"Finetuning Large Language Models for Vulnerability Detection","date":"2024-01-30","arxiv_id":"2401.17010","repositories_listed":1,"syntology":null},{"url":"/paper/how-far-have-we-gone-in-vulnerability","slug":"how-far-have-we-gone-in-vulnerability","title":"How Far Have We Gone in Vulnerability Detection Using Large Language Models","date":"2023-11-21","arxiv_id":"2311.12420","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-powered-smart-contract","slug":"large-language-model-powered-smart-contract","title":"Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives","date":"2023-10-02","arxiv_id":"2310.01152","repositories_listed":1,"syntology":null},{"url":"/paper/when-less-is-enough-positive-and-unlabeled","slug":"when-less-is-enough-positive-and-unlabeled","title":"When Less is Enough: Positive and Unlabeled Learning Model for Vulnerability Detection","date":"2023-08-21","arxiv_id":"2308.10523","repositories_listed":1,"syntology":null},{"url":"/paper/when-gpt-meets-program-analysis-towards","slug":"when-gpt-meets-program-analysis-towards","title":"GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis","date":"2023-08-07","arxiv_id":"2308.03314","repositories_listed":1,"syntology":null},{"url":"/paper/livable-exploring-long-tailed-classification","slug":"livable-exploring-long-tailed-classification","title":"LIVABLE: Exploring Long-Tailed Classification of Software Vulnerability Types","date":"2023-06-12","arxiv_id":"2306.06935","repositories_listed":1,"syntology":null},{"url":"/paper/dshgt-dual-supervisors-heterogeneous-graph","slug":"dshgt-dual-supervisors-heterogeneous-graph","title":"DSHGT: Dual-Supervisors Heterogeneous Graph Transformer -- A pioneer study of using heterogeneous graph learning for detecting software vulnerabilities","date":"2023-06-02","arxiv_id":"2306.01376","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-quantize-vulnerability-patterns","slug":"learning-to-quantize-vulnerability-patterns","title":"Learning to Quantize Vulnerability Patterns and Match to Locate Statement-Level Vulnerabilities","date":"2023-05-26","arxiv_id":"2306.06109","repositories_listed":1,"syntology":null},{"url":"/paper/the-earlybird-catches-the-bug-on-exploiting","slug":"the-earlybird-catches-the-bug-on-exploiting","title":"The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification","date":"2023-05-08","arxiv_id":"2305.04940","repositories_listed":1,"syntology":null},{"url":"/paper/an-unbiased-transformer-source-code-learning","slug":"an-unbiased-transformer-source-code-learning","title":"An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph","date":"2023-04-17","arxiv_id":"2304.11072","repositories_listed":1,"syntology":null},{"url":"/paper/diversevul-a-new-vulnerable-source-code","slug":"diversevul-a-new-vulnerable-source-code","title":"DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection","date":"2023-04-01","arxiv_id":"2304.00409","repositories_listed":1,"syntology":null},{"url":"/paper/illuminati-towards-explaining-graph-neural","slug":"illuminati-towards-explaining-graph-neural","title":"Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis","date":"2023-03-26","arxiv_id":"2303.14836","repositories_listed":1,"syntology":null},{"url":"/paper/deepdfa-dataflow-analysis-guided-efficient","slug":"deepdfa-dataflow-analysis-guided-efficient","title":"Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection","date":"2022-12-15","arxiv_id":"2212.08108","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepdfa-dataflow-analysis-guided-efficient#ran","syntology_url":"https://syntology.ai/paper/2212.08108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08108"}},"official":{"repos":["ISU-PAAL/DeepDFA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-information-theoretic-and-contrastive","slug":"an-information-theoretic-and-contrastive","title":"Statement-Level Vulnerability Detection: Learning Vulnerability Patterns Through Information Theory and Contrastive Learning","date":"2022-09-20","arxiv_id":"2209.10414","repositories_listed":1,"syntology":null},{"url":"/paper/cross-project-software-vulnerability-1","slug":"cross-project-software-vulnerability-1","title":"Cross Project Software Vulnerability Detection via Domain Adaptation and Max-Margin Principle","date":"2022-09-19","arxiv_id":"2209.10406","repositories_listed":1,"syntology":null},{"url":"/paper/mando-multi-level-heterogeneous-graph","slug":"mando-multi-level-heterogeneous-graph","title":"MANDO: Multi-Level Heterogeneous Graph Embeddings for Fine-Grained Detection of Smart Contract Vulnerabilities","date":"2022-08-28","arxiv_id":"2208.13252","repositories_listed":1,"syntology":null},{"url":"/paper/vulcnn-an-image-inspired-scalable","slug":"vulcnn-an-image-inspired-scalable","title":"VulCNN: An Image-inspired Scalable Vulnerability Detection System","date":"2022-06-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vulberta-simplified-source-code-pre-training","slug":"vulberta-simplified-source-code-pre-training","title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","date":"2022-05-25","arxiv_id":"2205.12424","repositories_listed":1,"syntology":null},{"url":"/paper/learning-program-semantics-with-code","slug":"learning-program-semantics-with-code","title":"Learning Program Semantics with Code Representations: An Empirical Study","date":"2022-03-22","arxiv_id":"2203.11790","repositories_listed":1,"syntology":null},{"url":"/paper/graphsearchnet-enhancing-gnns-via-capturing","slug":"graphsearchnet-enhancing-gnns-via-capturing","title":"GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search","date":"2021-11-04","arxiv_id":"2111.02671","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-machine-learning-techniques-for-1","slug":"a-survey-on-machine-learning-techniques-for-1","title":"A Survey on Machine Learning Techniques for Source Code Analysis","date":"2021-10-18","arxiv_id":"2110.09610","repositories_listed":1,"syntology":null},{"url":"/paper/regvd-revisiting-graph-neural-networks-for-1","slug":"regvd-revisiting-graph-neural-networks-for-1","title":"ReGVD: Revisiting Graph Neural Networks for Vulnerability Detection","date":"2021-10-14","arxiv_id":"2110.07317","repositories_listed":1,"syntology":null},{"url":"/paper/combining-graph-neural-networks-with-expert","slug":"combining-graph-neural-networks-with-expert","title":"Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection","date":"2021-07-24","arxiv_id":"2107.11598","repositories_listed":1,"syntology":null},{"url":"/paper/smart-contract-vulnerability-detection-from","slug":"smart-contract-vulnerability-detection-from","title":"Smart Contract Vulnerability Detection: From Pure Neural Network to Interpretable Graph Feature and Expert Pattern Fusion","date":"2021-06-17","arxiv_id":"2106.09282","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/smart-contract-vulnerability-detection-from#ran","syntology_url":"https://syntology.ai/paper/2106.09282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09282"}},"official":{"repos":["Messi-Q/AMEVulDetector"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/d2a-a-dataset-built-for-ai-based","slug":"d2a-a-dataset-built-for-ai-based","title":"D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis","date":"2021-02-16","arxiv_id":"2102.07995","repositories_listed":1,"syntology":null},{"url":"/paper/when-simple-is-better-than-complex-a-case","slug":"when-simple-is-better-than-complex-a-case","title":"Old but Gold: Reconsidering the value of feedforward learners for software analytics","date":"2021-01-15","arxiv_id":"2101.06319","repositories_listed":1,"syntology":null},{"url":"/paper/eth2vec-learning-contract-wide-code","slug":"eth2vec-learning-contract-wide-code","title":"Eth2Vec: Learning Contract-Wide Code Representations for Vulnerability Detection on Ethereum Smart Contracts","date":"2021-01-07","arxiv_id":"2101.02377","repositories_listed":1,"syntology":null},{"url":"/paper/stack-based-buffer-overflow-detection-using","slug":"stack-based-buffer-overflow-detection-using","title":"Stack-based Buffer Overflow Detection using Recurrent Neural Networks","date":"2020-12-30","arxiv_id":"2012.15116","repositories_listed":1,"syntology":null},{"url":"/paper/androshield-automated-android-applications","slug":"androshield-automated-android-applications","title":"AndroShield: Automated Android Applications Vulnerability Detection, a Hybrid Static and Dynamic Analysis Approach","date":"2019-10-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"core-benchmarking-llms-code-reasoning","title":"CORE: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks","date":"2025-07-03","arxiv_id":"2507.05269","repositories_listed":0,"syntology":null},{"url":null,"slug":"sv-llm-an-agentic-approach-for-soc-security","title":"SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models","date":"2025-06-25","arxiv_id":"2506.20415","repositories_listed":0,"syntology":null},{"url":null,"slug":"smart-llama-dpo-reinforced-large-language","title":"Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection","date":"2025-06-23","arxiv_id":"2506.18245","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-helpful-context-for-llm-based","title":"Identifying Helpful Context for LLM-based Vulnerability Repair: A Preliminary Study","date":"2025-06-13","arxiv_id":"2506.11561","repositories_listed":0,"syntology":null},{"url":null,"slug":"today-s-cat-is-tomorrow-s-dog-accounting-for","title":"Today's Cat Is Tomorrow's Dog: Accounting for Time-Based Changes in the Labels of ML Vulnerability Detection Approaches","date":"2025-06-13","arxiv_id":"2506.11939","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-driven-vulnerability-analysis-in-smart","title":"Ai-Driven Vulnerability Analysis in Smart Contracts: Trends, Challenges and Future Directions","date":"2025-06-07","arxiv_id":"2506.06735","repositories_listed":0,"syntology":null},{"url":null,"slug":"safegenbench-a-benchmark-framework-for","title":"SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code","date":"2025-06-06","arxiv_id":"2506.05692","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-dataset-evaluation-of-models-for","title":"A Multi-Dataset Evaluation of Models for Automated Vulnerability Repair","date":"2025-06-05","arxiv_id":"2506.04987","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainer-guided-targeted-adversarial-attacks","title":"Explainer-guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models","date":"2025-06-05","arxiv_id":"2506.05430","repositories_listed":0,"syntology":null},{"url":null,"slug":"lpass-linear-probes-as-stepping-stones-for","title":"LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs","date":"2025-05-30","arxiv_id":"2505.24451","repositories_listed":0,"syntology":null},{"url":null,"slug":"bugwhisperer-fine-tuning-llms-for-soc","title":"BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection","date":"2025-05-28","arxiv_id":"2505.22878","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-initial-exploration-of-fine-tuning-small","title":"An Initial Exploration of Fine-tuning Small Language Models for Smart Contract Reentrancy Vulnerability Detection","date":"2025-05-25","arxiv_id":"2505.19059","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-plan-execute-framework-for-smart","title":"Adaptive Plan-Execute Framework for Smart Contract Security Auditing","date":"2025-05-21","arxiv_id":"2505.15242","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-language-models-for-command","title":"Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects","date":"2025-05-21","arxiv_id":"2505.15088","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-the-trial-begin-a-mock-court-approach-to","title":"Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents","date":"2025-05-16","arxiv_id":"2505.10961","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-cloud-security-through-topic","title":"Enhancing the Cloud Security through Topic Modelling","date":"2025-05-01","arxiv_id":"2505.01463","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmpatronous-harnessing-the-power-of-llms-for","title":"LLMpatronous: Harnessing the Power of LLMs For Vulnerability Detection","date":"2025-04-25","arxiv_id":"2504.18423","repositories_listed":0,"syntology":null},{"url":"/paper/case-study-fine-tuning-small-language-models","slug":"case-study-fine-tuning-small-language-models","title":"Case Study: Fine-tuning Small Language Models for Accurate and Private CWE Detection in Python Code","date":"2025-04-23","arxiv_id":"2504.16584","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-mixup-inspired-augmentation","title":"A Study on Mixup-Inspired Augmentation Methods for Software Vulnerability Detection","date":"2025-04-22","arxiv_id":"2504.15632","repositories_listed":0,"syntology":null},{"url":null,"slug":"c2rust-bench-a-minimized-representative","title":"C2RUST-BENCH: A Minimized, Representative Dataset for C-to-Rust Transpilation Evaluation","date":"2025-04-21","arxiv_id":"2504.15144","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-based-vulnerability-analysis-of-nft-smart","title":"AI-Based Vulnerability Analysis of NFT Smart Contracts","date":"2025-04-18","arxiv_id":"2504.16113","repositories_listed":0,"syntology":null},{"url":null,"slug":"trace-gadgets-minimizing-code-context-for","title":"Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Prediction","date":"2025-04-18","arxiv_id":"2504.13676","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-ml-filters-to-help-automated","title":"Using ML filters to help automated vulnerability repairs: when it helps and when it doesn't","date":"2025-04-09","arxiv_id":"2504.07027","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-under-threat-symbolic-and-neural","title":"Reasoning Under Threat: Symbolic and Neural Techniques for Cybersecurity Verification","date":"2025-03-27","arxiv_id":"2503.22755","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-software-vulnerability-detection","title":"Enhancing Software Vulnerability Detection Using Code Property Graphs and Convolutional Neural Networks","date":"2025-03-23","arxiv_id":"2503.18175","repositories_listed":0,"syntology":null},{"url":null,"slug":"computing-modes-of-instability-of","title":"Computing Modes of Instability of Parameterized Nonlinear Systems for Vulnerability Assessment","date":"2025-03-16","arxiv_id":"2503.12298","repositories_listed":0,"syntology":null},{"url":null,"slug":"vulnerability-detection-from-formal","title":"Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview","date":"2025-03-13","arxiv_id":"2503.10784","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-llama-3-2-for-software","title":"Evaluating LLaMA 3.2 for Software Vulnerability Detection","date":"2025-03-10","arxiv_id":"2503.07770","repositories_listed":0,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":8,"papers_where_code_ran_first_page":"/task/vulnerability-detection/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/vulnerability-detection/papers/2","json":"/task/vulnerability-detection/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/vulnerability-detection/papers/3","json":"/task/vulnerability-detection/papers/3.json","rows":16},{"order":"ran","page":1,"of":1,"url":"/task/vulnerability-detection/papers/ran/1","json":"/task/vulnerability-detection/papers/ran/1.json","rows":8}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"29f4c365ae52a8bcaf4ad9226818228c7361a5c49fb9a4ea250115f9c8796278","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}