# What Malware Actually Does: An Empirical Analysis of Post-Infection Behavior Across Malware Families

DevFeed: [What Malware Actually Does: An Empirical Analysis of Post-Infection Behavior Across Malware Families](<https://devfeed.tech/articles/what-malware-actually-does-an-empirical-analysis-of-post-infection-behavior-across-malware-families-116134.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03774>)

Author: Emmanuela Andam, Emanuel S. Grant, Naima Kaabouch

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Malware](<https://devfeed.tech/topics/malware.md>), [Threat Research](<https://devfeed.tech/topics/threat-research.md>), [Graph Mining](<https://devfeed.tech/topics/graph-mining.md>)

Tags: [analysis](<https://devfeed.tech/tags/analysis.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [detection](<https://devfeed.tech/tags/detection.md>), [execution](<https://devfeed.tech/tags/execution.md>), [family](<https://devfeed.tech/tags/family.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [infection](<https://devfeed.tech/tags/infection.md>), [llm](<https://devfeed.tech/tags/llm.md>), [malware](<https://devfeed.tech/tags/malware.md>), [mitre](<https://devfeed.tech/tags/mitre.md>)

## AI overview

The paper analyzes post-infection behavior across 37 malware families using dynamic execution in CAPEv2. It represents behavioral traces as heterogeneous graphs with five node types and seven typed relationships, then reports that a voting ensemble using graph-derived features reaches 94.44% accuracy and 0.863 MCC, 7.4 percentage points higher in MCC than a flat behavioral baseline. A multiclass classifier distinguishes 24 families; the authors also characterize family-specific behavior across registry, network, process, and API dimensions. HeteroScan adds analyst-readable LLM reports with MITRE ATT&CK mappings based on observed behavior. These are abstract-level claims; no further experimental details are provided in the supplied text.

## Source excerpt

arXiv:2611.03774v1 Announce Type: new Abstract: Most malware detection research focuses on identifying whether a file is malicious before it executes. Far less attention goes to what happens after infection. This paper presents an empirical analysis of post-infection malware behavior across 37 families, grounded in dynamic sandbox execution using CAPEv2. Behavioral traces are modeled as heterogeneous graphs with five node types and seven typed edge relationships, preserving relational structure that flat feature vectors discard. A voting ensemble trained on graph-derived structural features achieves 94.44% accuracy and MCC of 0.863, outperforming a flat behavioral baseline by 7.4 percentage points in MCC. A multiclass classifier distinguishes 24 malware families, and a per-family behavioral fingerprint analysis characterizes post-infection activity across registry, network, process, and API dimensions. An LLM explanation layer generates analyst-readable reports with MITRE ATT&CK mappings grounded in observed behavioral evidence. The full pipeline is deployed as HeteroScan at https://ama-andam.github.io/heteroscan.