adversarial-training
π―Skillfrom pluginagentmarketplace/custom-plugin-ai-red-teaming
Performs adversarial training to systematically probe and identify potential vulnerabilities in AI systems through targeted testing scenarios.
Part of
pluginagentmarketplace/custom-plugin-ai-red-teaming(25 items)
Installation
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill adversarial-trainingNeed more details? View full documentation on GitHub β
More from this repository10
red-team-frameworks skill from pluginagentmarketplace/custom-plugin-ai-red-teaming
certifications-training skill from pluginagentmarketplace/custom-plugin-ai-red-teaming
prompt-hacking skill from pluginagentmarketplace/custom-plugin-ai-red-teaming
Performs privacy attacks to extract sensitive training data from AI models by inferring membership, attributes, and reconstructing training samples.
Automates comprehensive security testing for AI/ML systems, covering vulnerability, penetration, and compliance across APIs, models, and infrastructure.
rag-exploitation skill from pluginagentmarketplace/custom-plugin-ai-red-teaming
red-team-reporting skill from pluginagentmarketplace/custom-plugin-ai-red-teaming
benchmark-datasets skill from pluginagentmarketplace/custom-plugin-ai-red-teaming
vulnerability-discovery skill from pluginagentmarketplace/custom-plugin-ai-red-teaming
data-poisoning skill from pluginagentmarketplace/custom-plugin-ai-red-teaming