adversarial-training
CommunityFortify models with robust adversarial training.
Software Engineering#security#LLM#robustness#machine-learning#adversarial-training#training-pipelines
Authorpluginagentmarketplace
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill helps data scientists and engineers build more robust AI models by incorporating adversarial examples and attack simulations into the training process, reducing model brittleness under adversarial inputs.
Core Features & Use Cases
- Structured training configuration: supports standard adversarial training, TRADES, and certified approaches with clear input/output schemas.
- Comprehensive attack coverage: guides training against FGSM, PGD, CW, AutoAttack, and more to improve resilience.
- Use Case: You want to harden a text-generation model against prompt-injection and data-poisoning; run adversarial training and evaluate robustness metrics to quantify gains.
Quick Start
Use the adversarial-training skill to begin robust model training with the provided scripts and configuration assets.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferencesassets
💻 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: adversarial-training Download link: https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming/archive/main.zip#adversarial-training Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.