Systematic Hazard Analysis for Frontier AI using STPA

• URL: http://arxiv.org/abs/2506.01782v1
• Date: Mon, 02 Jun 2025 15:28:34 GMT
• Title: Systematic Hazard Analysis for Frontier AI using STPA
• Authors: Simon Mylius,
• Abstract summary: frontier AI companies currently do not describe in detail any structured approach to identifying and analysing hazards.<n>A (Systems-Theoretic Process Analysis) is a systematic methodology for identifying how complex systems can become unsafe, leading to hazards.<n>We evaluateA's ability to broaden the scope, improve traceability and strengthen the robustness of safety assurance for frontier AI systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deploy their models. Adoption of systematic approaches to risk modelling, based on established practices used in safety-critical industries, has been recommended, however frontier AI companies currently do not describe in detail any structured approach to identifying and analysing hazards. STPA (Systems-Theoretic Process Analysis) is a systematic methodology for identifying how complex systems can become unsafe, leading to hazards. It achieves this by mapping out controllers and controlled processes then analysing their interactions and feedback loops to understand how harmful outcomes could occur (Leveson & Thomas, 2018). We evaluate STPA's ability to broaden the scope, improve traceability and strengthen the robustness of safety assurance for frontier AI systems. Applying STPA to the threat model and scenario described in 'A Sketch of an AI Control Safety Case' (Korbak et al., 2025), we derive a list of Unsafe Control Actions. From these we select a subset and explore the Loss Scenarios that lead to them if left unmitigated. We find that STPA is able to identify causal factors that may be missed by unstructured hazard analysis methodologies thereby improving robustness. We suggest STPA could increase the safety assurance of frontier AI when used to complement or check coverage of existing AI governance techniques including capability thresholds, model evaluations and emergency procedures. The application of a systematic methodology supports scalability by increasing the proportion of the analysis that could be conducted by LLMs, reducing the burden on human domain experts.

Related papers

• Towards provable probabilistic safety for scalable embodied AI systems [79.31011047593492]
  Embodied AI systems are increasingly prevalent across various applications.<n> Ensuring their safety in complex operating environments remains a major challenge.<n>This Perspective offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications.
  arXiv  Detail & Related papers  (2025-06-05T15:46:25Z)
• Adapting Probabilistic Risk Assessment for AI [0.0]
  General-purpose artificial intelligence (AI) systems present an urgent risk management challenge.<n>Current methods often rely on selective testing and undocumented assumptions about risk priorities.<n>This paper introduces the probabilistic risk assessment (PRA) for AI framework.
  arXiv  Detail & Related papers  (2025-04-25T17:59:14Z)
• An Approach to Technical AGI Safety and Security [72.83728459135101]
  We develop an approach to address the risk of harms consequential enough to significantly harm humanity.<n>We focus on technical approaches to misuse and misalignment.<n>We briefly outline how these ingredients could be combined to produce safety cases for AGI systems.
  arXiv  Detail & Related papers  (2025-04-02T15:59:31Z)
• From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems [2.226040060318401]
  We translate System Theoretic Process Analysis (STPA) for analyzing AI operation and development processes. We focus on systems that rely on machine learning algorithms and conductedA on three case studies. We find that key concepts and steps of conducting anA readily apply, albeit with a few adaptations tailored for AI systems.
  arXiv  Detail & Related papers  (2024-10-29T20:43:18Z)
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents [53.717918131568936]
  Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction.<n>Foundation models as the "brain" of EAI agents for high-level task planning have shown promising results.<n>However, the deployment of these agents in physical environments presents significant safety challenges.<n>This study introduces EARBench, a novel framework for automated physical risk assessment in EAI scenarios.
  arXiv  Detail & Related papers  (2024-08-08T13:19:37Z)
• Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress? [59.96471873997733]
  We propose an empirical foundation for developing more meaningful safety metrics and define AI safety in a machine learning research context.<n>We aim to provide a more rigorous framework for AI safety research, advancing the science of safety evaluations and clarifying the path towards measurable progress.
  arXiv  Detail & Related papers  (2024-07-31T17:59:24Z)
• Risks of ignoring uncertainty propagation in AI-augmented security pipelines [5.692289204193087]
  The use of AI technologies is being integrated into the secure development of software-based systems.<n>No previous work has estimated the uncertainty of AI-augmented systems given the propagation of errors in the pipeline.<n>We provide the formal underpinnings for capturing uncertainty propagation, develop a simulator to quantify uncertainty, and evaluate the simulation of propagating errors with one case study.
  arXiv  Detail & Related papers  (2024-07-14T19:02:20Z)
• AI Hazard Management: A framework for the systematic management of root causes for AI risks [0.0]
  This paper introduces the AI Hazard Management (AIHM) framework. It provides a structured process to systematically identify, assess, and treat AI hazards. It builds upon an AI hazard list from a comprehensive state-of-the-art analysis.
  arXiv  Detail & Related papers  (2023-10-25T15:55:50Z)
• Leveraging Traceability to Integrate Safety Analysis Artifacts into the Software Development Process [51.42800587382228]
  Safety assurance cases (SACs) can be challenging to maintain during system evolution. We propose a solution that leverages software traceability to connect relevant system artifacts to safety analysis models. We elicit design rationales for system changes to help safety stakeholders analyze the impact of system changes on safety.
  arXiv  Detail & Related papers  (2023-07-14T16:03:27Z)
• Model evaluation for extreme risks [46.53170857607407]
  Further progress in AI development could lead to capabilities that pose extreme risks, such as offensive cyber capabilities or strong manipulation skills. We explain why model evaluation is critical for addressing extreme risks.
  arXiv  Detail & Related papers  (2023-05-24T16:38:43Z)
• Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks [70.76757529955577]
  This paper revisits prior work in this scope from the perspective of state-wise safe RL. We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection. To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
  arXiv  Detail & Related papers  (2022-12-12T06:30:17Z)
• Quantitative AI Risk Assessments: Opportunities and Challenges [7.35411010153049]
  Best way to reduce risks is to implement comprehensive AI lifecycle governance.<n>Risks can be quantified using metrics from the technical community.<n>This paper explores these issues, focusing on the opportunities, challenges, and potential impacts of such an approach.
  arXiv  Detail & Related papers  (2022-09-13T21:47:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.