A Scalable Framework for Safety Assurance of Self-Driving Vehicles based on Assurance 2.0

• URL: http://arxiv.org/abs/2510.00092v1
• Date: Tue, 30 Sep 2025 16:13:03 GMT
• Title: A Scalable Framework for Safety Assurance of Self-Driving Vehicles based on Assurance 2.0
• Abstract summary: Assurance 2.0 is a modern framework developed to address the assurance challenges of increasingly complex, adaptive, and autonomous systems.<n>It introduces reusable assurance theories and explicit counterarguments (defeaters) to enhance rigor, transparency, and adaptability.<n> limitations persist in confidence measurement, residual doubt management, automation support, and the practical handling of defeaters and confirmation bias.
• Score: 3.2877342344625777
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Assurance 2.0 is a modern framework developed to address the assurance challenges of increasingly complex, adaptive, and autonomous systems. Building on the traditional Claims-Argument-Evidence (CAE) model, it introduces reusable assurance theories and explicit counterarguments (defeaters) to enhance rigor, transparency, and adaptability. It supports continuous, incremental assurance, enabling innovation without compromising safety. However, limitations persist in confidence measurement, residual doubt management, automation support, and the practical handling of defeaters and confirmation bias. This paper presents \textcolor{black}{a set of decomposition frameworks to identify a complete set of safety arguments and measure their corresponding evidence.} Grounded in the Assurance 2.0 paradigm, the framework is instantiated through a structured template and employs a three-tiered decomposition strategy. \textcolor{black}{A case study regarding the application of the decomposition framework in the end-to-end (E2E) AI-based Self-Driving Vehicle (SDV) development is also presented in this paper.} At the top level, the SDV development is divided into three critical phases: Requirements Engineering (RE), Verification and Validation (VnV), and Post-Deployment (PD). Each phase is further decomposed according to its Product Development Lifecycle (PDLC). To ensure comprehensive coverage, each PDLC is analyzed using an adapted 5M1E model (Man, Machine, Method, Material, Measurement, and Environment). Originally developed for manufacturing quality control, the 5M1E model is reinterpreted and contextually mapped to the assurance domain. This enables a multi-dimensional decomposition that supports fine-grained traceability of safety claims, evidence, and potential defeaters.

Related papers

• Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels [53.63220028820581]
  Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction.<n>We define trustworthy embodied intelligence as the sustained capacity to execute specified tasks reliably.
  arXiv  Detail & Related papers  (2026-07-28T17:50:44Z)
• Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety [74.88019498257665]
  General-purpose models often struggle to reliably identify and understand real-world multimodal risks.<n>We present Yuvion VL, a family of multimodal large language models purpose-built for content and AI safety.
  arXiv  Detail & Related papers  (2026-06-23T18:00:08Z)
• Making Embodied AI Reliable: A Community Agenda from Testing to Formal Verification [38.209854965937495]
  Embodied AI systems are increasingly deployed in open-world environments.<n>This article argues that reliability in embodied AI is inherently a lifecycle assurance problem.
  arXiv  Detail & Related papers  (2026-06-02T12:58:40Z)
• Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications [51.56484100374058]
  We present an automated self-testing framework that introduces quality gates with evidence-based release decisions.<n>We evaluate the framework through a longitudinal case study of an internally deployed multi-agent conversational AI system.
  arXiv  Detail & Related papers  (2026-03-13T20:44:15Z)
• Trustworthy AI Posture (TAIP): A Framework for Continuous AI Assurance of Agentic Systems at Horizontal and Vertical scale [1.0896567381206714]
  Point-in-time, document-based audits cannot keep pace with non deterministic behaviour.<n>Crisis is dual-scale: vertically, governance and control obligations change faster than frameworks can operationalise them.<n>Risk-based regulation now requires organisations to demonstrate ongoing control adequacy and effectiveness.<n>This paper reframes trustworthiness as a continuously generated signal rather than a static certificate.
  arXiv  Detail & Related papers  (2026-02-15T10:49:47Z)
• Towards Continuous Assurance with Formal Verification and Assurance Cases [0.5483130283061118]
  We propose a unified Continuous Assurance Framework that integrates design-time, runtime, and evolution-time assurance within a traceable, model-driven workflow.<n>We demonstrate our approach on a nuclear inspection robot scenario, and discuss its alignment with the Trilateral AI Principles.
  arXiv  Detail & Related papers  (2025-11-17T18:42:38Z)
• SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization [79.14563283347773]
  Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities.<n>Cross-modal couplings can produce unsafe semantics even when individual inputs are benign.<n>We propose SafeGRPO, a self-rewarded multimodal safety alignment framework.
  arXiv  Detail & Related papers  (2025-11-17T05:09:49Z)
• AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning (AIRS) Framework [31.261980405052938]
  Assurance for artificial intelligence (AI) systems remains fragmented across software supply-chain security, adversarial machine learning, and governance documentation.<n>This paper introduces the AI Risk Scanning (AIRS) Framework, a threat-model-based, evidence-generating framework designed to operationalize AI assurance.
  arXiv  Detail & Related papers  (2025-11-16T16:10:38Z)
• Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions [51.56484100374058]
  Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes.<n>This gap, driven by mutually cognitive biases in both humans and artificial intelligence (AI) systems, threatens the defensibility of valuations and sustainability of investments in the sector.<n>This report describes a framework emerging from systematic qualitative assessment across 7 frontier-grade LLMs and 3 market-facing venture vignettes under time pressure.
  arXiv  Detail & Related papers  (2025-11-10T22:24:21Z)
• Automating Steering for Safe Multimodal Large Language Models [58.36932318051907]
  We introduce a modular and adaptive inference-time intervention technology, AutoSteer, without requiring any fine-tuning of the underlying model.<n>AutoSteer incorporates three core components: (1) a novel Safety Awareness Score (SAS) that automatically identifies the most safety-relevant distinctions among the model's internal layers; (2) an adaptive safety prober trained to estimate the likelihood of toxic outputs from intermediate representations; and (3) a lightweight Refusal Head that selectively intervenes to modulate generation when safety risks are detected.
  arXiv  Detail & Related papers  (2025-07-17T16:04:55Z)
• Justified Evidence Collection for Argument-based AI Fairness Assurance [7.65321625950609]
  This paper introduces a systems-engineering-driven framework, supported by software tooling, to operationalise a dynamic approach to argument-based assurance in two stages.<n>The framework's effectiveness is demonstrated through an illustrative case study in finance, with a focus on supporting fairness-related arguments.
  arXiv  Detail & Related papers  (2025-05-12T21:05:33Z)
• T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models [88.63040835652902]
  Text to video models are vulnerable to jailbreak attacks, where specially crafted prompts bypass safety mechanisms and lead to the generation of harmful or unsafe content.<n>We propose T2VShield, a comprehensive and model agnostic defense framework designed to protect text to video models from jailbreak threats.<n>Our method systematically analyzes the input, model, and output stages to identify the limitations of existing defenses.
  arXiv  Detail & Related papers  (2025-04-22T01:18:42Z)
• On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective [377.2483044466149]
  Generative Foundation Models (GenFMs) have emerged as transformative tools.<n>Their widespread adoption raises critical concerns regarding trustworthiness across dimensions.<n>This paper presents a comprehensive framework to address these challenges through three key contributions.
  arXiv  Detail & Related papers  (2025-02-20T06:20:36Z)
• AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons [62.374792825813394]
  This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability.<n>The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories.
  arXiv  Detail & Related papers  (2025-02-19T05:58:52Z)
• DRIVE: Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Driving [1.4104119587524289]
  Recent advancements in autonomous driving have seen a paradigm shift towards end-to-end learning paradigms. These models often sacrifice interpretability, posing significant challenges to trust, safety, and regulatory compliance. We introduce DRIVE, a comprehensive framework designed to improve the dependability and stability of explanations in end-to-end unsupervised driving models.
  arXiv  Detail & Related papers  (2024-09-16T14:40:47Z)
• Automating Semantic Analysis of System Assurance Cases using Goal-directed ASP [1.2189422792863451]
  We present our approach to enhancing Assurance 2.0 with semantic rule-based analysis capabilities. We examine the unique semantic aspects of assurance cases, such as logical consistency, adequacy, indefeasibility, etc.
  arXiv  Detail & Related papers  (2024-08-21T15:22:43Z)

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.