media-voicefake-benchmark

Community

Benchmark voice deepfake detection with SSML.

Authorwuyoscar
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This template provides a structured benchmark for evaluating voice deepfake detection pipelines using SSML-formatted samples across five attack categories, ensuring realistic, controlled test data.

Core Features & Use Cases

  • SSML-based attack samples to assess robustness of detection systems.
  • Voice-attack coverage (voice cloning, emotion manipulation, identity spoofing, ransom deepfake, and authority impersonation) for comprehensive testing.
  • Reusable framework for security research and benchmark development, with an explicit replacement step for PLACEHOLDER_SPEECH to simulate credible social-engineering scripts.

Quick Start

Replace PLACEHOLDER_SPEECH with realistic SSML content across all attack categories and run the validation workflow.

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: media-voicefake-benchmark
Download link: https://github.com/wuyoscar/ISC-Bench/archive/main.zip#media-voicefake-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.