The paper introduces a comprehensive taxonomy and auditing framework to assess the collective coverage of existing LLM attack benchmarks, revealing significant and systematic gaps in current testing m…

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 proposes an automated, standardized framework to empirically compare the security quality of code generated through human-only, LLM-only, and hybrid collaboration methods.

This paper provides the first comprehensive Systematization of Knowledge (SoK) on the security aspects of LLM-as-a-Judge (LaaJ) systems, identifying key vulnerabilities and proposing a taxonomy for fu…

The paper introduces codebadger, a Model Context Protocol (MCP) server that integrates Joern's Code Property Graph (CPG) with LLMs, enabling large language models to perform large-scale, semantic prog…

The paper evaluates multi-LLM strategies for secure code generation, finding that hybrid pipelines combining ensembling, static analysis, and patching achieve the strongest security performance, outpe…

The paper introduces a novel multi-LLM orchestration system combined with symbolic execution to successfully detect memory vulnerabilities in uncompilable, incomplete Rust CVE code snippets, achieving…

The paper introduces SEC-bench Pro, a rigorous benchmark for evaluating LLM-based bug hunting on complex software, finding that even advanced agents struggle with long-horizon security tasks.

The paper introduces Heimdall, an automated pipeline that uses LLMs and formal verification to safely and automatically migrate legacy, potentially buggy eBPF programs written in C to memory-safe Rust…

AsmRAG is a novel framework that improves malware detection by treating it as an evidence-based retrieval task using a code-specialized LLM, achieving high accuracy while providing transparent forensi…

The paper introduces SIGIL, a novel framework that cryptographically seals the entire lifecycle of LLM skills, ensuring verifiable integrity from publication through runtime execution to prevent suppl…

The paper analyzes GitHub security advisories for LLM-integrated open-source systems, finding that while most vulnerabilities map to existing code-level weaknesses, the architectural risks like Supply…

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…

QASecClaw, a multi-agent LLM system, significantly improves the accuracy of Static Application Security Testing (SAST) by using specialized LLM agents to filter out false positives, achieving an F1 sc…

The paper introduces False Security Confidence (FSC), a new metric to measure the inherent prevalence of security vulnerabilities in code generated by LLMs that are otherwise functionally correct, eve…

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…

This study conducts a large-scale longitudinal analysis of CodeQL, finding that while the tool is effective at detecting vulnerabilities, its detection capabilities are not guaranteed to be stable acr…

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…

This paper proposes a structured pipeline using LLMs to generate and evaluate obfuscated XSS payloads, demonstrating that while LLMs can generate samples, they currently struggle to ensure payloads ma…

This study assesses the effectiveness and cost of four modern LLMs in detecting vulnerabilities that span multiple functions (interprocedural dependencies), finding that Gemini 3 Flash offers strong c…