Archive - Detoxio AI

Build Secure SOC AI Incident Investigation Agent, Part 1

Mitigate Prompt Injections, Jailbreaks, Data Leaks and Misalignment Issues

12 hrs ago •

Guardrails in Practice: Measuring Llama-PG vs. Detoxio’s 300 M ‘AI Firewall'

What 20 adversarial prompts reveal about modern safety stacks

Jun 23 •

May 2025

February 2025

Hands-On AI Red Teaming Course

Feb 9 •

January 2025

Distilled Deepseek Models

Safety Evaluation Report

Jan 30 •

OWASP Top 10 Vulnerabilities in LLM Applications

An Overview and Introduction

Jan 26 •

1:01:25

🚀 Happy New Year from Detoxio AI! 🎉

with an exciting upgrade to our AI Red Teaming Tool!

Jan 9 •

0:43

December 2024

Evaluate any open source model for safety and security using Automated AI Red Teaming

Demo on IBM Granite 3.1 8B !!

Dec 20, 2024 •

7:16

102 - Agentic AI - Build a Chatbot and perform Safety Testing

Building a Chat Interface with Sarvam-1 and Gradio

Dec 7, 2024 •

11:12

Watch Live - Safety Evaluation of Meta LLAMA 3.3 70B with Detoxio Automated AI Red Teaming Platform

Watch now (8 mins) | Our platform took 30 mins to find 120 unsafe responses from Meta LLama 3.3!!!

Dec 7, 2024 •

8:01

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts