mlsanityData to 7 Oct 2026

Semantic Preprocessing for LLM-based Malware Analysis

arXiv 2506.12113 ↗First posted 13 Jun 2025cs.CR cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

In a context of malware analysis, numerous approaches rely on Artificial Intelligence to handle a large volume of data. However, these techniques focus on data view (images, sequences) and not on an expert's view. Noticing this issue, we propose a preprocessing that focuses on expert knowledge to improve malware semantic analysis and result interpretability. We propose a new preprocessing method which creates JSON reports for Portable Executable files. These reports gather features from both static and behavioral analysis, and incorporate packer signature detection, MITRE ATT&CK and Malware Behavior Catalog (MBC) knowledge. The purpose of this preprocessing is to gather a semantic representation of binary files, understandable by malware analysts, and that can enhance AI models' explainability for malicious files analysis. Using this preprocessing to train a Large Language Model for Malware classification, we achieve a weighted-average F1-score of 0.94 on a complex dataset, representative of market reality.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 15 of its 33 references that are in the map. First posted on arXiv 13 Jun 2025.

Builds on

15 of 33 references.

References · 15

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 327
  4. 2018EMBER: An Open Dataset for Training Static PE Malware Machine Learning Modelscited by 164
  5. 2017Malware Detection by Eating a Whole EXEcited by 114
  6. 2018Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learningcited by 60
  7. 2020SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detectioncited by 49
  8. 2018Microsoft Malware Classification Challengecited by 46
  9. 2025EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifierscited by 18
  10. 2022MERLIN -- Malware Evasion with Reinforcement LearnINgcited by 10
  11. 2022AI-based Malware and Ransomware Detection Modelscited by 7
  12. 2021Towards an Automated Pipeline for Detecting and Classifying Malware through Machine Learningcited by 6
3 more
  1. 2023MalDICT: Benchmark Datasets on Malware Behaviors, Platforms, Exploitation, and Packerscited by 4
  2. 2024Image-Based Malware Classification Using QR and Aztec Codescited by 2
  3. 2024Use of Multi-CNNs for Section Analysis in Static Malware Detectioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025BEACON: Behavioral Malware Classification with Large Language Model Embeddings and Deep Learningcited by 0
  2. 2026LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attributioncited by 0
  3. 2026ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzerscited by 0