adversarial-robustness
CommunitySecure ML models against adversarial evasion.
Software Engineering#model-evaluation#ml-security#adversarial-robustness#robustness-evaluation#adversarial-attack#input-normalization
Authormaruakshay
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Adversarial robustness gaps reveal how human-intended meaning can be misinterpreted by models under tiny input perturbations, threatening safety and reliability.
Core Features & Use Cases
- Evaluate resilience of safety classifiers and content filters against evasion attacks.
- Analyze transferability of adversarial examples across model versions and configurations.
- Use cases include validating guardrails in production, conducting red-team assessments, and strengthening model evaluation pipelines.
Quick Start
Run an adversarial-robustness assessment against your deployed model to identify vulnerabilities and validate defenses.
Dependency Matrix
Required Modules
None requiredComponents
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: adversarial-robustness Download link: https://github.com/maruakshay/mii-ai-security/archive/main.zip#adversarial-robustness 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 471,000+ vetted skills library on demand.