Statistical Scenario Modelling and Lookalike Distributions for Multi-Variate AI Risk

• URL: http://arxiv.org/abs/2502.14491v1
• Date: Thu, 20 Feb 2025 12:14:54 GMT
• Title: Statistical Scenario Modelling and Lookalike Distributions for Multi-Variate AI Risk
• Authors: Elija Perrier,
• Abstract summary: We show how scenario modelling can be used to model AI risk holistically.<n>We show how lookalike distributions from phenomena analogous to AI can be used to estimate AI impacts in the absence of directly observable data.
• Score: 0.6526824510982799
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating AI safety requires statistically rigorous methods and risk metrics for understanding how the use of AI affects aggregated risk. However, much AI safety literature focuses upon risks arising from AI models in isolation, lacking consideration of how modular use of AI affects risk distribution of workflow components or overall risk metrics. There is also a lack of statistical grounding enabling sensitisation of risk models in the presence of absence of AI to estimate causal contributions of AI. This is in part due to the dearth of AI impact data upon which to fit distributions. In this work, we address these gaps in two ways. First, we demonstrate how scenario modelling (grounded in established statistical techniques such as Markov chains, copulas and Monte Carlo simulation) can be used to model AI risk holistically. Second, we show how lookalike distributions from phenomena analogous to AI can be used to estimate AI impacts in the absence of directly observable data. We demonstrate the utility of our methods for benchmarking cumulative AI risk via risk analysis of a logistic scenario simulations.

Related papers

• Adapting Probabilistic Risk Assessment for AI [0.0]
  General-purpose artificial intelligence (AI) systems present an urgent risk management challenge. Current methods often rely on selective testing and undocumented assumptions about risk priorities. This paper introduces the probabilistic risk assessment (PRA) for AI framework.
  arXiv  Detail & Related papers  (2025-04-25T17:59:14Z)
• Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation [0.7889270818022226]
  We show how existing AI benchmarks can be used to facilitate the creation of risk estimates. We describe the results of a pilot study in which experts use information from Cybench, an AI benchmark, to generate probability estimates.
  arXiv  Detail & Related papers  (2025-03-06T10:39:47Z)
• Computational Safety for Generative AI: A Signal Processing Perspective [65.268245109828]
  computational safety is a mathematical framework that enables the quantitative assessment, formulation, and study of safety challenges in GenAI.<n>We show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts.<n>We discuss key open research challenges, opportunities, and the essential role of signal processing in computational AI safety.
  arXiv  Detail & Related papers  (2025-02-18T02:26:50Z)
• Detecting Discrepancies Between AI-Generated and Natural Images Using Uncertainty [91.64626435585643]
  We propose a novel approach for detecting AI-generated images by leveraging predictive uncertainty to mitigate misuse and associated risks.<n>The motivation arises from the fundamental assumption regarding the distributional discrepancy between natural and AI-generated images.<n>We propose to leverage large-scale pre-trained models to calculate the uncertainty as the score for detecting AI-generated images.
  arXiv  Detail & Related papers  (2024-12-08T11:32:25Z)
• A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation [0.3413711585591077]
  As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks. This paper introduces a novel formal framework for categorizing and mitigating these emergent security risks. We identify previously under-explored risks, including latent space exploitation, multi-modal cross-attack vectors, and feedback-loop-induced model degradation.
  arXiv  Detail & Related papers  (2024-10-15T02:51:32Z)
• 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)
• Adversarial Robustness of Open-source Text Classification Models and Fine-Tuning Chains [11.379606061113348]
  Open-source AI models and fine-tuning chains face new security risks, such as adversarial attacks. This paper aims to explore the adversarial robustness of open-source AI models and their chains formed by the upstream-downstream relationships via fine-tuning.
  arXiv  Detail & Related papers  (2024-08-06T05:17:17Z)
• Measuring Bias in AI Models: An Statistical Approach Introducing N-Sigma [19.072543709069087]
  We analyze statistical approaches to measure biases in automatic decision-making systems. We propose a novel way to measure the biases in machine learning models using a statistical approach based on the N-Sigma method.
  arXiv  Detail & Related papers  (2023-04-26T16:49:25Z)
• Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles [86.9067793493874]
  We propose efficient mechanisms to characterize and generate testing scenarios using a state-of-the-art driving simulator. We use our method to characterize real driving data from the Next Generation Simulation (NGSIM) project. We rank the scenarios by defining metrics based on the complexity of avoiding accidents and provide insights into how the AV could have minimized the probability of incurring an accident.
  arXiv  Detail & Related papers  (2021-03-12T17:00:23Z)
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models [64.03398193325572]
  Inference attacks against Machine Learning (ML) models allow adversaries to learn about training data, model parameters, etc. We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing. Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models.
  arXiv  Detail & Related papers  (2021-02-04T11:35:13Z)
• Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction [55.569050872780224]
  We present an online framework for safe crowd-robot interaction based on risk-sensitive optimal control, wherein the risk is modeled by the entropic risk measure. Our modular approach decouples the crowd-robot interaction into learning-based prediction and model-based control. A simulation study and a real-world experiment show that the proposed framework can accomplish safe and efficient navigation while avoiding collisions with more than 50 humans in the scene.
  arXiv  Detail & Related papers  (2020-09-12T02:02:52Z)
• On Safety Assessment of Artificial Intelligence [0.0]
  We show that many models of artificial intelligence, in particular machine learning, are statistical models. Part of the budget of dangerous random failures for the relevant safety integrity level needs to be used for the probabilistic faulty behavior of the AI system. We propose a research challenge that may be decisive for the use of AI in safety related systems.
  arXiv  Detail & Related papers  (2020-02-29T14:05:28Z)

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.