RuleForge is an automated system that generates and validates detection rules for web vulnerabilities from structured CVE templates, significantly improving detection accuracy and reducing false posit…

The paper introduces CrossCommitVuln-Bench, a benchmark dataset demonstrating that many real-world Python vulnerabilities are introduced across multiple commits, making them invisible to standard per-…

The paper analyzes a dataset of agent skills, demonstrating that different security scanners (VirusTotal, static analysis, SkillSpector) rarely agree, necessitating a layered governance approach for s…

The paper analyzes a dataset of agent skills, demonstrating that different security scanners (VirusTotal, static analysis, SkillSpector) rarely agree on maliciousness, necessitating layered security g…

The paper introduces a novel, large-scale dataset of vulnerable code snippets linked to CAPEC and CWE, generated using advanced LLMs, to improve automatic vulnerability detection.

VulGD is a dynamic, open-access graph database that aggregates cybersecurity data from multiple sources and uses LLM embeddings to improve vulnerability representation and risk assessment.

The paper introduces CyberCertBench, a new benchmark suite for evaluating LLMs against industry cybersecurity certifications, finding that while frontier models perform well on general knowledge, thei…

VIPER-MCP is a novel, end-to-end automated framework that detects and dynamically confirms the exploitability of taint-style vulnerabilities in Model Context Protocol (MCP) servers, achieving high-fid…

The paper introduces a validated, consensus-labeled prompt bank that separates requests for executable malicious code (weapons) from requests for general harmful security knowledge, providing a more g…

FixV2W introduces a knowledge graph embedding approach to significantly improve the accuracy of inconsistent CVE-CWE mappings in public vulnerability databases, achieving high prediction rates for exp…

SkillSieve introduces a three-layer hierarchical framework to detect malicious AI agent skills, achieving high F1 scores (0.920) on a large-scale benchmark while maintaining low operational costs.

This study conducts a large-scale empirical analysis of third-party LLM agent skills, identifying that credential leakage is a pervasive, cross-modal issue primarily caused by debug logging and result…

This paper systematically surveys adaptive and AI-augmented security testing, concluding that a major gap exists—structural-adaptive fragmentation—where current systems fail to integrate structural pr…

The paper introduces NICE, a declarative framework that uses NixOS to build and automatically validate reproducible environments for demonstrating software vulnerabilities (CVEs), thereby improving th…

The paper introduces SynthChain, a comprehensive, multi-source synthetic testbed and dataset that demonstrates that detecting advanced software supply chain attacks requires fusing evidence from multi…

The paper introduces VULNSCOUT-C, a compact, specialized transformer model that achieves state-of-the-art performance in C code vulnerability detection while maintaining low inference cost, making it…

The paper introduces the CAI Dataset, a massive, multi-terabyte corpus of real-world, hands-on cybersecurity LLM trajectories, designed to address the performance bottleneck caused by expert operator…

The paper introduces CSTM-Bench, a comprehensive benchmark and evaluation framework demonstrating that standard session-bound AI guardrails fail against sophisticated, cross-session attacks that accum…

FuzzingBrain V2 is a multi-agent LLM system that significantly improves automated vulnerability discovery by ensuring all reported bugs are fuzzer-reproducible and handling complex cross-function depe…

The paper introduces a deterministic method to automatically synthesize initial SIEM detection rules (Sigma rules) from attack simulation findings, ensuring full traceability back to the specific orig…