{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2202.13169","title":"A Systematic Evaluation of Large Language Models of Code","created":"2022-02-26","cited_by_count":363},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"1909.03496","title":"Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks","created":"2019-09-08","cited_by_count":272},{"id":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155},{"id":"2403.18624","title":"Vulnerability Detection with Code Language Models: How Far Are We?","created":"2024-03-27","cited_by_count":139},{"id":"2302.13007","title":"AugGPT: Leveraging ChatGPT for Text Data Augmentation","created":"2023-02-25","cited_by_count":130},{"id":"2404.08144","title":"LLM Agents can Autonomously Exploit One-day Vulnerabilities","created":"2024-04-11","cited_by_count":128},{"id":"2405.17238","title":"IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities","created":"2024-05-27","cited_by_count":103},{"id":"2304.00409","title":"DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection","created":"2023-04-01","cited_by_count":102},{"id":"2312.12575","title":"LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks","created":"2023-12-19","cited_by_count":97},{"id":"1807.06756","title":"SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities","created":"2018-07-18","cited_by_count":92},{"id":"2107.08760","title":"CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software","created":"2021-07-19","cited_by_count":91},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82},{"id":"2406.11147","title":"Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG","created":"2024-06-17","cited_by_count":68},{"id":"2310.01726","title":"Large Language Models for Test-Free Fault Localization","created":"2023-10-03","cited_by_count":67},{"id":"2411.09523","title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","created":"2024-11-14","cited_by_count":65},{"id":"2311.16169","title":"Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities","created":"2023-11-16","cited_by_count":59},{"id":"2206.07585","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","created":"2022-06-15","cited_by_count":54},{"id":"2305.18607","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","created":"2023-05-29","cited_by_count":52},{"id":"2205.12424","title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","created":"2022-05-25","cited_by_count":51},{"id":"2102.07995","title":"D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis","created":"2021-02-16","cited_by_count":49},{"id":"2310.01152","title":"Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives","created":"2023-10-02","cited_by_count":48},{"id":"2310.09810","title":"ChatGPT for Vulnerability Detection, Classification, and Repair: How Far Are We?","created":"2023-10-15","cited_by_count":44},{"id":"2403.16073","title":"Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications","created":"2024-03-24","cited_by_count":41},{"id":"2401.17010","title":"Finetuning Large Language Models for Vulnerability Detection","created":"2024-01-30","cited_by_count":40},{"id":"2001.02350","title":"VulDeeLocator: A Deep Learning-based Fine-grained Vulnerability Detector","created":"2020-01-08","cited_by_count":37},{"id":"2406.03718","title":"Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning","created":"2024-06-06","cited_by_count":30},{"id":"1902.02595","title":"A Manually-Curated Dataset of Fixes to Vulnerabilities of Open-Source Software","created":"2019-02-07","cited_by_count":28},{"id":"2312.17677","title":"Prompt Fuzzing for Fuzz Driver Generation","created":"2023-12-29","cited_by_count":27},{"id":"2402.15302","title":"How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries","created":"2024-02-23","cited_by_count":27},{"id":"2304.11686","title":"Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting","created":"2023-04-23","cited_by_count":23},{"id":"2404.02056","title":"Multitask-based Evaluation of Open-Source LLM on Software Vulnerability","created":"2024-04-02","cited_by_count":23},{"id":"2307.12469","title":"How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generation","created":"2023-07-24","cited_by_count":21},{"id":"2005.11613","title":"How Effective are Smart Contract Analysis Tools? Evaluating Smart Contract Static Analysis Tools Using Bug Injection","created":"2020-05-23","cited_by_count":20},{"id":"2403.14274","title":"Multi-role Consensus through LLMs Discussions for Vulnerability Detection","created":"2024-03-21","cited_by_count":19},{"id":"2007.04771","title":"SmartBugs: A Framework to Analyze Solidity Smart Contracts","created":"2020-07-08","cited_by_count":18},{"id":"2407.16235","title":"Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection","created":"2024-07-23","cited_by_count":18},{"id":"2403.19096","title":"SCALE: Constructing Structured Natural Language Comment Trees for Software Vulnerability Detection","created":"2024-03-28","cited_by_count":17},{"id":"2409.03454","title":"How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizes","created":"2024-09-05","cited_by_count":17},{"id":"2309.15324","title":"DefectHunter: A Novel LLM-Driven Boosted-Conformer-based Code Vulnerability Detection Mechanism","created":"2023-09-27","cited_by_count":14},{"id":"2307.06616","title":"SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?","created":"2023-07-13","cited_by_count":13},{"id":"2401.01269","title":"LLbezpeky: Leveraging Large Language Models for Vulnerability Detection","created":"2024-01-02","cited_by_count":13},{"id":"1703.02458","title":"End-to-End Prediction of Buffer Overruns from Raw Source Code via Neural Memory Networks","created":"2017-03-07","cited_by_count":10},{"id":"2301.03943","title":"Rethinking Smart Contract Fuzzing: Fuzzing With Invocation Ordering and Important Branch Revisiting","created":"2023-01-10","cited_by_count":10},{"id":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8},{"id":"2404.00287","title":"Evaluating Large Language Models for Line-Level Vulnerability Localization","created":"2024-03-30","cited_by_count":7},{"id":"2303.06853","title":"Representation Learning for Stack Overflow Posts: How Far are We?","created":"2023-03-13","cited_by_count":6},{"id":"2309.15474","title":"CCBERT: Self-Supervised Code Change Representation Learning","created":"2023-09-27","cited_by_count":6},{"id":"2406.18894","title":"Assessing the Effectiveness of LLMs in Android Application Vulnerability Analysis","created":"2024-06-27","cited_by_count":6},{"id":"2408.03489","title":"Harnessing the Power of LLMs in Source Code Vulnerability Detection","created":"2024-08-07","cited_by_count":6},{"id":"2404.09599","title":"Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data Augmentation","created":"2024-04-15","cited_by_count":5},{"id":"2501.02628","title":"Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets","created":"2025-01-05","cited_by_count":4},{"id":"1708.02380","title":"Ghera: A Repository of Android App Vulnerability Benchmarks","created":"2017-08-08","cited_by_count":3},{"id":"2407.14372","title":"SCoPE: Evaluating LLMs for Software Vulnerability Detection","created":"2024-07-19","cited_by_count":3},{"id":"2408.02329","title":"From Generalist to Specialist: Exploring CWE-Specific Vulnerability Detection","created":"2024-08-05","cited_by_count":3},{"id":"2410.07573","title":"RealVul: Can We Detect Vulnerabilities in Web Applications with LLM?","created":"2024-10-10","cited_by_count":3},{"id":"2409.10574","title":"Detection Made Easy: Potentials of Large Language Models for Solidity Vulnerabilities","created":"2024-09-15","cited_by_count":2},{"id":"2411.17343","title":"Assessing Vulnerability in Smart Contracts: The Role of Code Complexity Metrics in Security Analysis","created":"2024-11-26","cited_by_count":2}],"next_cursor":null}