Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2507.17118 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909701699010560 |
|---|---|
| author | Pitale, Mandar Frtunikj, Jelena Priyadershi, Abhinaw Singh, Vasu Spence, Maria |
| author_facet | Pitale, Mandar Frtunikj, Jelena Priyadershi, Abhinaw Singh, Vasu Spence, Maria |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17118 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HySafe-AI: Hybrid Safety Architectural Analysis Framework for AI Systems: A Case Study Pitale, Mandar Frtunikj, Jelena Priyadershi, Abhinaw Singh, Vasu Spence, Maria Artificial Intelligence 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. |
| title | HySafe-AI: Hybrid Safety Architectural Analysis Framework for AI Systems: A Case Study |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.17118 |