Archive2

Red Team Your LLM with BeaverTails

Ensuring your LLM can safely handle harmful content is critical for production deployments.

How to run CyberSecEval

Your LLM's security is only as strong as its weakest prompt.

Leveraging Promptfoo for EU AI Act Compliance

Beginning on February 2, 2025, the first prohibitions against certain AI systems will go into force in the European Union through the EU AI Act..

How to Red Team an Ollama Model

Want to test the safety and security of a model hosted on Ollama? This guide shows you how to use Promptfoo to systematically probe for vulnerabilities through adversarial testing (red teaming)..

How to Red Team a HuggingFace Model

Want to break a HuggingFace model? This guide shows you how to use Promptfoo to systematically probe for vulnerabilities through adversarial testing (red teaming)..

Introducing GOAT—Promptfoo's Latest Strategy

We're excited to announce the deployment of Promptfoo's latest strategy, GOAT, to jailbreak multi-turn conversations..

RAG Data Poisoning: Key Concepts Explained

How attackers can manipulate AI responses by corrupting the knowledge base..

Does Fuzzing LLMs Actually Work?

Fuzzing has been a tried and true method in pentesting for years.

How Do You Secure RAG Applications?

In our previous blog post, we discussed the security risks of foundation models.

Prompt Injection: A Comprehensive Guide

In August 2024, security researcher Johann Rehberger uncovered a critical vulnerability in Microsoft 365 Copilot: through a sophisticated prompt injection attack, he demonstrated how sensitive company data could be secretly exfiltrated..