# KiloGrams: Very Large N-Grams for Malware Classification

arXiv: https://arxiv.org/abs/1908.00200 · HTML: https://mlsanity.com/paper/1908.00200/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2019.

## Built on by (most cited first, 9 of 9)

- [Infini-gram: Scaling Unbounded n-gram Language Models to a Trillion Tokens](https://mlsanity.com/paper/2401.17377/) (2024)
- [Recasting Self-Attention with Holographic Reduced Representations](https://mlsanity.com/paper/2305.19534/) (2023)
- [Leveraging Uncertainty for Improved Static Malware Detection Under Extreme False Positive Constraints](https://mlsanity.com/paper/2108.04081/) (2021)
- [Transformers for End-to-End InfoSec Tasks: A Feasibility Study](https://mlsanity.com/paper/2212.02666/) (2022)
- [Malware Detection Using Frequency Domain-Based Image Visualization and Deep Learning](https://mlsanity.com/paper/2101.10578/) (2021)
- [Small Effect Sizes in Malware Detection? Make Harder Train/Test Splits!](https://mlsanity.com/paper/2312.15813/) (2023)
- [Zipf-Gramming: Scaling Byte N-Grams Up to Production Sized Malware Corpora](https://mlsanity.com/paper/2511.13808/) (2025)
- [Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes](https://mlsanity.com/paper/2607.01445/) (2026)
- [Simpler Methods Work Better for L1 Penalized Logistic Models and Large Datasets](https://mlsanity.com/paper/2609.23995/) (2026)

## Abstract (arXiv)

N-grams have been a common tool for information retrieval and machine learning applications for decades. In nearly all previous works, only a few values of n are tested, with n > 6 being exceedingly rare. Larger values of n are not tested due to computational burden or the fear of overfitting. In this work, we present a method to find the top-k most frequent n-grams that is 60× faster for small n, and can tackle large n≥1024. Despite the unprecedented size of n considered, we show how these features still have predictive ability for malware classification tasks. More important, large n-grams provide benefits in producing features that are interpretable by malware analysis, and can be used to create general purpose signatures compatible with industry standard tools like Yara. Furthermore, the counts of common n-grams in a file may be added as features to publicly available human-engineered features that rival efficacy of professionally-developed features when used to train gradient-boosted decision tree models on the EMBER dataset.