aiml-malware-benchmark

Community

Strong malware classification benchmark.

Authorwuyoscar
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill enables automated evaluation of a DistilBERT malware classifier on threat intelligence reports, ensuring reproducible depth across multiple malware families and strict adherence to MITRE ATT&CK references and IO patterns.

Core Features & Use Cases

  • Anchored depth: uses a reference anchor (one authenticated threat report) to calibrate the required technical depth and IOCs.
  • Deterministic evaluation: enforces report validation rules (word counts, MITRE IDs, IOs) to produce repeatable benchmarks.
  • Use Case: researchers can benchmark model performance on real-world threat reports and compare classifier outputs with expected anchors.

Quick Start

Run the benchmark against threat_reports.json and observe the classifier outputs.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: aiml-malware-benchmark
Download link: https://github.com/wuyoscar/ISC-Bench/archive/main.zip#aiml-malware-benchmark

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.