AI

Romana Vasyleha

AI Product Security Newsletter - Vol I. Issue 5

New Products: Securing AI Applications with AI & Prompt Guard With our recent launch of AI Guard & Prompt Guard Pangea now offers the broadest set of AI Security Guardrails in the industry. AI Guard and Prompt Guard are two cutting-edge solutions des...

AI Access Granted: RAG Apps with Identity and Access Control

Pranav Shikarpur

AI Access Granted: RAG Apps with Identity and Access Control

As companies increasingly turn to AI-driven systems to support customer interactions through systems like chatbots and streamline operations, Retrieval-Augmented Generation (RAG) has become a popular framework for enhancing large language models (LLM...

Keith Casey

Building Authorization in AI Apps

When we look at the current state of generative AI, we think of products like ChatGPT, Google Gemini, Claude, and similar. Those are all publicly available tools trained on public data and useful for general topics for a general audience. But if we e...

Introducing Pangea Prompt Guard and AI Guard to Secure AI Applications

John Gamble

Introducing Pangea Prompt Guard and AI Guard to Secure AI Applications

I have spent much of the past two months on the road speaking with organizations of all industries about their AI application initiatives and I am struck both by their techno optimism and by the depth of their security concerns. The pace of innovatio...

The Hidden Threat of AI: Understanding and Mitigating Prompt Injection Attacks

Pranav Shikarpur

The Hidden Threat of AI: Understanding and Mitigating Prompt Injection Attacks

In recent years, large language models (LLMs) like GPT-3 and GPT-4 have revolutionized how enterprises, especially in healthcare and finance, process and interact with data. These models enhance customer support, automate decision-making, and generat...

Where AI-Powered Software is Going,
We Need Secure, Paved Roads

John Gamble

Where AI-Powered Software is Going, We Need Secure, Paved Roads

Do you remember when and where you first used an AI-powered product that caused you to question reality? I do. In the spring of 2022, I tested a synthetic text-to-voice app that was so uncannily realistic that I briefly questioned if it was truly AI ...

Is Your LLM Leaking Sensitive Data? A Developer’s Guide to Preventing Sensitive Information Disclosure

Pranav Shikarpur

Is Your LLM Leaking Sensitive Data? A Developer’s Guide to Preventing Sensitive Information Disclosure

Your data has been exposed—and not because of a classic bug, but because your LLM accidentally leaked it. Sensitive information disclosure is a growing concern, especially with the rise of Large Language Models (LLMs) in our apps. This vulnerability ...

Querying LLMs with Pangea and GitHub Copilot Chat

Michael Weinberger

Querying LLMs with Pangea and GitHub Copilot Chat

In the ever-evolving landscape of AI code generation and developer assistance tools, providing users with accurate and relevant information quickly is crucial. To help ensure that developers can swiftly and easily add security features to their produ...

Building security services for application developers.