{"total":62,"rows":[{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71,"area":"agents"},{"id":"2410.13886","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","created":"2024-10-11","cited_by_count":65,"area":"agents"},{"id":"2504.21039","title":"Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report","created":"2025-04-28","cited_by_count":31,"area":null},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2605.14153","title":"ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents","created":"2026-05-13","cited_by_count":19,"area":"agents"},{"id":"2503.11917","title":"A Framework for Evaluating Emerging Cyberattack Capabilities of AI","created":"2025-03-14","cited_by_count":16,"area":null},{"id":"2507.14201","title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","created":"2025-07-14","cited_by_count":15,"area":"agents"},{"id":"2408.09304","title":"CyberPal.AI: Empowering LLMs with Expert-Driven Cybersecurity Instructions","created":"2024-08-17","cited_by_count":12,"area":null},{"id":"2509.20166","title":"CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning","created":"2025-09-24","cited_by_count":12,"area":"lr"},{"id":"2510.24317","title":"Cybersecurity AI Benchmark (CAIBench): A Meta-Benchmark for Evaluating Cybersecurity AI Agents","created":"2025-10-28","cited_by_count":12,"area":"agents"},{"id":"2601.22975","title":"Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2603.01246","title":"Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders","created":"2026-03-01","cited_by_count":10,"area":"alignment"},{"id":"2505.20630","title":"SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis","created":"2025-05-27","cited_by_count":8,"area":"lr"},{"id":"2509.23571","title":"Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2509.23573","title":"Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2503.04299","title":"Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2505.19973","title":"DFIR-Metric: A Benchmark Dataset for Evaluating Large Language Models in Digital Forensics and Incident Response","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2506.00739","title":"DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments","created":"2025-05-31","cited_by_count":4,"area":"agents"},{"id":"2507.02964","title":"Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2510.14113","title":"Toward Cybersecurity-Expert Small Language Models","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2511.01144","title":"AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2603.13517","title":"CTI-REALM: Benchmark to Evaluate Agent Performance on Security Detection Rule Generation Capabilities","created":"2026-03-13","cited_by_count":4,"area":"agents"},{"id":"2503.09586","title":"Auspex: Building Threat Modeling Tradecraft into an Artificial Intelligence-based Copilot","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2506.10467","title":"Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications","created":"2025-06-12","cited_by_count":3,"area":"lr"},{"id":"2601.07880","title":"Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management Visibility","created":"2026-01-11","cited_by_count":3,"area":"agents"},{"id":"2409.15072","title":"Evaluating the Usability of LLMs in Threat Intelligence Enrichment","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2506.12094","title":"Military AI Cyber Agents (MAICAs) Constitute a Global Threat to Critical Infrastructure","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2507.06252","title":"False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systems","created":"2025-07-05","cited_by_count":2,"area":null},{"id":"2509.06921","title":"Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2510.27080","title":"Adapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation","created":"2025-10-31","cited_by_count":2,"area":"rag"},{"id":"2602.00513","title":"Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2603.09452","title":"CyberThreat-Eval: Can Large Language Models Automate Real-World Threat Research?","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2606.02674","title":"Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security Reasoning","created":"2026-06-01","cited_by_count":2,"area":"agents"},{"id":"2608.02407","title":"Antares: Foundation Models for Agentic Vulnerability Localization","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2608.18613","title":"CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence","created":"2026-08-19","cited_by_count":2,"area":"agents"},{"id":"2505.11565","title":"ACSE-Eval: Can LLMs threat model real-world cloud infrastructure?","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2512.06781","title":"From Description to Score: Can LLMs Quantify Vulnerabilities?","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2601.14556","title":"Constructing Multi-label Hierarchical Classification Models for MITRE ATT&CK Text Tagging","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2601.21083","title":"OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence","created":"2026-01-28","cited_by_count":1,"area":"agents"},{"id":"2601.22159","title":"RedSage: A Cybersecurity Generalist LLM","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.18235","title":"Toward Reliable, Safe, and Secure LLMs for Scientific Applications","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2604.20389","title":"CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2606.18166","title":"Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.19605","title":"FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2607.05842","title":"Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2608.04317","title":"Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2509.05331","title":"ForensicsData: A Digital Forensics Dataset for Large Language Models","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.19485","title":"Identifying and Addressing User-level Security Concerns in Smart Homes Using \"Smaller\" LLMs","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.20768","title":"RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines","created":"2025-10-23","cited_by_count":0,"area":"rag"},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2603.14911","title":"Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.00072","title":"XekRung Technical Report","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.24765","title":"CyberMaskQA: A Privacy-Aware Benchmark for Evaluating Large Language Models in Cybersecurity Question Answering","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2608.13608","title":"Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2609.00604","title":"NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.01671","title":"Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.21344","title":"CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.33521","title":"LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35561","title":"RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.17018","title":"LLM Evaluation is a Forecasting Problem","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}