Jev and CodeGraph for security review
The typesafe-security-review project combines Jev’s probability judgments with a code graph and OWASP/CWE data for low-cost security scanning.
Eryma: An LLM Security Project Using Jev
This project focuses on LLM security, using a modern decision model like Jev as a buffer layer and testing it with Garak, achieving a 98.86% improvement in detection hits.
اليوم اعلن لكم عن مشروعي Eryma المشروع مختص ب LLM security استخدمت طبقات عازلة باستخدام decision model زي Jev المودل الحديث اختبرت امان المشروع باستخدام Garak (generative AI red-teaming & assessment kit) الطبقات العازلة سوت تحسن بنسبة 98.86% في تفعيل ال detector hits ل garak
· 2 likesOpen on X
More like this
Jev Delivers 5x Cheaper and More Accurate Security Pipeline Results
A user shares experience using Jev in a security pipeline: over 5x cheaper, faster, and more accurate than smaller, dumber models.
Jev Use Cases and Demo in AI Security
Introduces Jev use cases and a demo in AI security, leveraging its choice-and-probability model with Unity AI Gateway and MLflow integration for safety checks.
