Hamm-grams are a new class of fixed-length regular expressions over bytes with single-character wildcards, mined efficiently with LSH and clustering to yield more robust features than n-grams for malware classification and detection.
Joyce, Derek Everett, Maya Fuchs, Edward Raff, and James Holt
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
BatteryMFormer is a multi-level Transformer that adds an aging-condition-aware decoder, meta degradation pattern memory, and dual-view encoder to forecast battery state-of-health trajectories from early operational data and outperforms baselines on four domains.
The paper releases two adversarial malware datasets (44k family-labelled, 33k type-labelled) with high evasion rates and demonstrates that 0.5% poisoning injection raises evasion from 26.1% to 92.8%.
Cybersecurity's scale, adversaries, labeling issues, and operational demands make it the superior test-case for general AI progress over NLP or computer vision.
citing papers explorer
-
Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes
Hamm-grams are a new class of fixed-length regular expressions over bytes with single-character wildcards, mined efficiently with LSH and clustering to yield more robust features than n-grams for malware classification and detection.
-
BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting
BatteryMFormer is a multi-level Transformer that adds an aging-condition-aware decoder, meta degradation pattern memory, and dual-view encoder to forecast battery state-of-health trajectories from early operational data and outperforms baselines on four domains.
-
Building an Adversarial Malware Dataset by Family and Type: Generation, Evasion, and Poisoning Evaluation
The paper releases two adversarial malware datasets (44k family-labelled, 33k type-labelled) with high evasion rates and demonstrates that 0.5% poisoning injection raises evasion from 26.1% to 92.8%.
-
Cybersecurity is the True Frontier for Generative AI Success or Failure
Cybersecurity's scale, adversaries, labeling issues, and operational demands make it the superior test-case for general AI progress over NLP or computer vision.