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.
Universal suffix attack on Jev model
A study finds that one short suffix flips 43% of unseen documents for the Jev model; a suffix from one task flips 90-100% of samples in other tasks, and the attack finds it in minutes.
One short suffix flips 43% of unseen documents for the Jev model One suffix from one task flips 90 to 100% of samples in other tasks, and the attack finds it in minutes. Subscribe: https://aimatterin.substack.com #AISecurity #Microsoft #ArXiv https://aimatter.in/2026/10/30/one-short-suffix-flips-43-of-unseen-documents-for/…
· 0 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.
