A static packer identifier using a Graph Matching Network and clustering reaches 93.7% macro F1 with 10 samples per packer, 98.3% with 100, and 100% recall on Themida.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PackHero: A Scalable Graph-based Approach for Efficient Packer Identification
A static packer identifier using a Graph Matching Network and clustering reaches 93.7% macro F1 with 10 samples per packer, 98.3% with 100, and 100% recall on Themida.