# AI security digest for 2025-10-29

Canonical page: https://jonathanglass.cloud/ai-security/2025-10-29.html

Each item is the publisher's title, date, and excerpt.

## Introducing gpt-oss-safeguard

- Source: OpenAI News
- Date: 2025-10-29
- URL: https://openai.com/index/introducing-gpt-oss-safeguard
- Publisher excerpt: OpenAI introduces gpt-oss-safeguard—open-weight reasoning models for safety classification that let developers apply and iterate on custom policies.

## gpt-oss-safeguard technical report

- Source: OpenAI News
- Date: 2025-10-29
- URL: https://openai.com/index/gpt-oss-safeguard-technical-report
- Publisher excerpt: gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order to label content under that policy. In this report, we describe gpt-oss-safeguard’s capabilities and provide our baseline safety evaluations on the gpt-oss-safeguard models, using the underlying gpt-oss models as a baseline. For more information about the development and architecture of the underlying... (excerpt trimmed)
