# HySafe-AI: Hybrid Safety Architectural Analysis Framework for AI Systems: A Case Study

arXiv: https://arxiv.org/abs/2507.17118 · HTML: https://mlsanity.com/paper/2507.17118/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 23 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying](https://mlsanity.com/paper/2306.17770/) (2023)
- [A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective](https://mlsanity.com/paper/2405.05173/) (2024)
- [Empowering Autonomous Driving with Large Language Models: A Safety Perspective](https://mlsanity.com/paper/2312.00812/) (2023)
- [VisualBackProp: efficient visualization of CNNs](https://mlsanity.com/paper/1611.05418/) (2016)
- [DeepVO: A Deep Learning approach for Monocular Visual Odometry](https://mlsanity.com/paper/1611.06069/) (2016)
- [Joint Perception and Prediction for Autonomous Driving: A Survey](https://mlsanity.com/paper/2412.14088/) (2024)
- [Systematic Hazard Analysis for Frontier AI using STPA](https://mlsanity.com/paper/2506.01782/) (2025)
- [Inherent Diverse Redundant Safety Mechanisms for AI-based Software Elements in Automotive Applications](https://mlsanity.com/paper/2402.08208/) (2024)
- [MSF3DDETR: Multi-Sensor Fusion 3D Detection Transformer for Autonomous Driving](https://mlsanity.com/paper/2210.15316/) (2022)
- [Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning](https://mlsanity.com/paper/2410.06347/) (2024)

## Abstract (arXiv)

AI has become integral to safety-critical areas like autonomous driving systems (ADS) and robotics. The architecture of recent autonomous systems are trending toward end-to-end (E2E) monolithic architectures such as large language models (LLMs) and vision language models (VLMs). In this paper, we review different architectural solutions and then evaluate the efficacy of common safety analyses such as failure modes and effect analysis (FMEA) and fault tree analysis (FTA). We show how these techniques can be improved for the intricate nature of the foundational models, particularly in how they form and utilize latent representations. We introduce HySAFE-AI, Hybrid Safety Architectural Analysis Framework for AI Systems, a hybrid framework that adapts traditional methods to evaluate the safety of AI systems. Lastly, we offer hints of future work and suggestions to guide the evolution of future AI safety standards.