Symbolicate-Enrich-Sample recovers symbols and call graphs from Windows binaries, enriches functions with LLM labels on reachability and risk, and produces a prioritized ~22K-function shortlist from 7.2M total via importance sampling.
Sift or get off the PoC: Applying information retrieval to vulnerability research with SiftRank, 2025.https://arxiv.org/abs/2512.06155
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research
Symbolicate-Enrich-Sample recovers symbols and call graphs from Windows binaries, enriches functions with LLM labels on reachability and risk, and produces a prioritized ~22K-function shortlist from 7.2M total via importance sampling.