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.
Jev Prompt Injection Lab
Jev judges whether an input message or instruction looks like a prompt injection, and flags, blocks, or allows it based on your threshold. Jev assesses the risk; your software decides what to do.
3. prompt injection lab input: a message or instruction Jev: judges whether it looks like a prompt injection code: uses your threshold to flag, block or allow it Jev judges the risk. your software decides what to do.
· 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.
