# Emerging Practices in Frontier AI Safety Frameworks

arXiv: https://arxiv.org/abs/2503.04746 · HTML: https://mlsanity.com/paper/2503.04746/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 1 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Built on by (most cited first, 6 of 6)

- [Systematic Hazard Analysis for Frontier AI using STPA](https://mlsanity.com/paper/2506.01782/) (2025)
- [Embodied AI: Emerging Risks and Opportunities for Policy Action](https://mlsanity.com/paper/2509.00117/) (2025)
- [The 2025 OpenAI Preparedness Framework does not guarantee any AI risk mitigation practices: a proof-of-concept for affordance analyses of AI safety policies](https://mlsanity.com/paper/2509.24394/) (2025)
- [Unified Threat Detection and Mitigation Framework (UTDMF): Combating Prompt Injection, Deception, and Bias in Enterprise-Scale Transformers](https://mlsanity.com/paper/2510.04528/) (2025)
- [Principles and Guidelines for Randomized Controlled Trials in AI Evaluation](https://mlsanity.com/paper/2605.02050/) (2026)
- [Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks](https://mlsanity.com/paper/2608.25390/) (2026)

## Abstract (arXiv)

As part of the Frontier AI Safety Commitments agreed to at the 2024 AI Seoul Summit, many AI developers agreed to publish a safety framework outlining how they will manage potential severe risks associated with their systems. This paper summarises current thinking from companies, governments, and researchers on how to write an effective safety framework. We outline three core areas of a safety framework - risk identification and assessment, risk mitigation, and governance - and identify emerging practices within each area. As safety frameworks are novel and rapidly developing, we hope that this paper can serve both as an overview of work to date and as a starting point for further discussion and innovation.