FuzzyAI
1,337A powerful tool for automated LLM fuzzing from CyberArk.
DetectionPost-generationFull HITLExperimentalTier 2BEnvironment
Maturity tier details
Computed tier: 2B(raw score 4.25). Effective tier: 2B.
Facets:documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_commit=2stars=1.25
Source of truth:pipeline/maturity/score.py
Description
CyberArk FuzzyAI is an automated LLM fuzzer: evolves adversarial prompts over many generations to find vulnerabilities in deployed LLM applications. Integrates with popular model providers and produces reproducible attack traces.
Why it's included
Fuzz-based branch of LLM vulnerability scanning — adds evolutionary prompt search alongside the fixed-probe scanners like garak.
Addresses failure modes
- Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
- Fabrication — Generating reference to non-existent APIs, packages, or symbols.
Techniques
evolutionary-prompt-fuzzingjailbreak-searchreproducible-traces