CodeQL detected 171 CVEs total, with 83 caught by a prior version before the fix; detections were often actionable within the vulnerable file but not stable across tool versions.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
RealVuln benchmark finds security-specialized scanners outperform general-purpose LLMs and rule-based SAST tools on hand-labeled vulnerable Python code under F3 scoring, with all artifacts released.
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.
PoisonCap uses a new poison capability format to deliver strict use-after-free and initialization safety for CHERI systems with no fundamental overhead over Cornucopia baselines.
Text fine-tuning of 8B LLMs on C/C++ vulnerability data inflates cross-language false-positive rates through surface-cue memorization, which an AST inference probe can partially reverse while direct AST fine-tuning cannot.
citing papers explorer
-
NESA: Relational Neuro-Symbolic Static Program Analysis
NESA presents a neuro-symbolic framework that decomposes static analyses into policy-defined sub-problems solved by parsers and LLMs to enable compilation-free customizable analysis with reduced hallucinations.