Workflow for Safe-AI

• URL: http://arxiv.org/abs/2503.14563v2
• Date: Thu, 20 Mar 2025 07:32:39 GMT
• Title: Workflow for Safe-AI
• Authors: Suzana Veljanovska, Hans Dermot Doran,
• Abstract summary: Development and deployment of safe and dependable AI models is crucial in applications where functional safety is a key concern.<n>This work proposes a transparent, complete, yet flexible and lightweight workflow that highlights both reliability and qualifiability.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The development and deployment of safe and dependable AI models is crucial in applications where functional safety is a key concern. Given the rapid advancement in AI research and the relative novelty of the safe-AI domain, there is an increasing need for a workflow that balances stability with adaptability. This work proposes a transparent, complete, yet flexible and lightweight workflow that highlights both reliability and qualifiability. The core idea is that the workflow must be qualifiable, which demands the use of qualified tools. Tool qualification is a resource-intensive process, both in terms of time and cost. We therefore place value on a lightweight workflow featuring a minimal number of tools with limited features. The workflow is built upon an extended ONNX model description allowing for validation of AI algorithms from their generation to runtime deployment. This validation is essential to ensure that models are validated before being reliably deployed across different runtimes, particularly in mixed-criticality systems. Keywords-AI workflows, safe-AI, dependable-AI, functional safety, v-model development

Related papers

• AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement [73.0700818105842]
  We introduce AISafetyLab, a unified framework and toolkit that integrates representative attack, defense, and evaluation methodologies for AI safety. AISafetyLab features an intuitive interface that enables developers to seamlessly apply various techniques. We conduct empirical studies on Vicuna, analyzing different attack and defense strategies to provide valuable insights into their comparative effectiveness.
  arXiv  Detail & Related papers  (2025-02-24T02:11:52Z)
• Flow: Modularized Agentic Workflow Automation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)
• ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning [48.536695794883826]
  We present ActSafe, a novel model-based RL algorithm for safe and efficient exploration. We show that ActSafe guarantees safety during learning while also obtaining a near-optimal policy in finite time. In addition, we propose a practical variant of ActSafe that builds on latest model-based RL advancements.
  arXiv  Detail & Related papers  (2024-10-12T10:46:02Z)
• Model Developmental Safety: A Retention-Centric Method and Applications in Vision-Language Models [75.8161094916476]
  We study how to develop a pretrained vision-language model, specifically the CLIP model, for acquiring new capabilities or improving existing capabilities of image classification.<n>Our experiments on improving vision perception capabilities on autonomous driving and scene recognition datasets demonstrate the efficacy of the proposed approach.
  arXiv  Detail & Related papers  (2024-10-04T22:34:58Z)
• An Early-Stage Workflow Proposal for the Generation of Safe and Dependable AI Classifiers [0.0]
  The generation and execution of qualifiable safe and dependable AI models, necessitates definition of a transparent, complete yet adaptable and preferably lightweight workflow. This early-stage work proposes such a workflow basing it on a an extended ONNX model description. A use case provides one foundations of this body of work which we expect to be extended by other, third party use-cases.
  arXiv  Detail & Related papers  (2024-10-01T14:00:53Z)
• ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems [80.69865295743149]
  This work attempts to study using LLM-based agents to design collaborative AI systems autonomously.<n>Based on ComfyBench, we develop ComfyAgent, a framework that empowers agents to autonomously design collaborative AI systems by generating.<n>While ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks.
  arXiv  Detail & Related papers  (2024-09-02T17:44:10Z)
• Hybrid Convolutional Neural Networks with Reliability Guarantee [0.0]
  We propose redundant execution as a well-known technique that can be used to ensure reliable execution of the AI model. This generic technique will extend the application scope of AI-accelerators that do not feature well-documented safety or dependability properties.
  arXiv  Detail & Related papers  (2024-05-08T15:39:38Z)
• Science based AI model certification for untrained operational environments with application in traffic state estimation [1.2186759689780324]
  The expanding role of Artificial Intelligence (AI) in diverse engineering domains highlights the challenges associated with deploying AI models in new operational environments. This paper proposes a science-based certification methodology to assess the viability of employing pre-trained data-driven models in untrained operational environments.
  arXiv  Detail & Related papers  (2024-03-21T03:01:25Z)
• Inherent Diverse Redundant Safety Mechanisms for AI-based Software Elements in Automotive Applications [1.6495054381576084]
  This paper explores the role and challenges of Artificial Intelligence (AI) algorithms in autonomous driving systems. A primary concern relates to the ability (and necessity) of AI models to generalize beyond their initial training data. This paper investigates the risk associated with overconfident AI models in safety-critical applications like autonomous driving.
  arXiv  Detail & Related papers  (2024-02-13T04:15:26Z)
• Scaling #DNN-Verification Tools with Efficient Bound Propagation and Parallel Computing [57.49021927832259]
  Deep Neural Networks (DNNs) are powerful tools that have shown extraordinary results in many scenarios. However, their intricate designs and lack of transparency raise safety concerns when applied in real-world applications. Formal Verification (FV) of DNNs has emerged as a valuable solution to provide provable guarantees on the safety aspect.
  arXiv  Detail & Related papers  (2023-12-10T13:51:25Z)
• 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)
• Enabling Automated Machine Learning for Model-Driven AI Engineering [60.09869520679979]
  We propose a novel approach to enable Model-Driven Software Engineering and Model-Driven AI Engineering. In particular, we support Automated ML, thus assisting software engineers without deep AI knowledge in developing AI-intensive systems.
  arXiv  Detail & Related papers  (2022-03-06T10:12:56Z)
• Tools and Practices for Responsible AI Engineering [0.5249805590164901]
  We present two new software libraries that address critical needs for responsible AI engineering. hydra-zen dramatically simplifies the process of making complex AI applications, and their behaviors reproducible. The rAI-toolbox is designed to enable methods for evaluating and enhancing the robustness of AI-models.
  arXiv  Detail & Related papers  (2022-01-14T19:47:46Z)

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.