QuerySec
Back to Home

AI Security Case Studies

Explore our successful penetration testing engagements in AI and machine learning systems, from foundation models to agentic systems.

Featured Case Study

Real World Vulnerabilities in the OWASP LLM Top 10 2025

A comprehensive analysis of real-world vulnerabilities in Large Language Models, based on the OWASP Top 10 for LLM Applications 2025.

Read Case Study →

All Case Studies

LLM SecurityMay 2024

OWASP LLM Top 10 Implementation

Comprehensive security assessment and remediation of a foundation model against the OWASP LLM Top 10 vulnerabilities.

Read More →
Agentic SecurityApril 2024

Multi-Agent System Security Assessment

Penetration testing of an autonomous agent system, focusing on prompt injection and agent manipulation vulnerabilities.

Read More →
ML SecurityMarch 2024

ML Model Security Testing

Security assessment of a production ML application, including model inversion and adversarial example testing.

Read More →
AI SecurityFebruary 2024

AI Service Security Assessment

Comprehensive security testing of an AI-powered service, including API security and model deployment vulnerabilities.

Read More →
LLM SecurityJanuary 2024

RAG System Security Testing

Security assessment of a Retrieval-Augmented Generation system, focusing on data leakage and prompt injection.

Read More →
ML SecurityDecember 2023

ML Pipeline Security Assessment

End-to-end security testing of an ML pipeline, from data ingestion to model deployment and monitoring.

Read More →

Ready to Secure Your AI Systems?

Our team of AI security experts can help you identify and remediate vulnerabilities in your ML and GenAI systems.