Indexing AI Risks with Incidents, Issues, and Variants

• URL: http://arxiv.org/abs/2211.10384v1
• Date: Fri, 18 Nov 2022 17:32:19 GMT
• Title: Indexing AI Risks with Incidents, Issues, and Variants
• Authors: Sean McGregor, Kevin Paeth, Khoa Lam
• Abstract summary: backlog of "issues" that do not meet database's incident ingestion criteria have accumulated. Similar to databases in aviation and computer security, the AIID proposes to adopt a two-tiered system for indexing AI incidents.
• Score: 5.8010446129208155
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Two years after publicly launching the AI Incident Database (AIID) as a collection of harms or near harms produced by AI in the world, a backlog of "issues" that do not meet its incident ingestion criteria have accumulated in its review queue. Despite not passing the database's current criteria for incidents, these issues advance human understanding of where AI presents the potential for harm. Similar to databases in aviation and computer security, the AIID proposes to adopt a two-tiered system for indexing AI incidents (i.e., a harm or near harm event) and issues (i.e., a risk of a harm event). Further, as some machine learning-based systems will sometimes produce a large number of incidents, the notion of an incident "variant" is introduced. These proposed changes mark the transition of the AIID to a new version in response to lessons learned from editing 2,000+ incident reports and additional reports that fall under the new category of "issue."

Related papers

• 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. We show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts. 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)
• Standardised schema and taxonomy for AI incident databases in critical digital infrastructure [2.209921757303168]
  The rapid deployment of Artificial Intelligence in critical digital infrastructure introduces significant risks. Existing databases lack the granularity as well as the standardized structure required for consistent data collection and analysis. This work proposes a standardized schema and taxonomy for AI incident databases, enabling detailed and structured documentation of AI incidents across sectors.
  arXiv  Detail & Related papers  (2025-01-28T15:59:01Z)
• Lessons for Editors of AI Incidents from the AI Incident Database [2.5165775267615205]
  The AI Incident Database (AIID) is a project that catalogs AI incidents and supports further research by providing a platform to classify incidents. This study reviews the AIID's dataset of 750+ AI incidents and two independent ambiguities applied to these incidents to identify common challenges to indexing and analyzing AI incidents. We report mitigations to make incident processes more robust to uncertainty related to cause, extent of harm, severity, or technical details of implicated systems.
  arXiv  Detail & Related papers  (2024-09-24T19:46:58Z)
• Risks and NLP Design: A Case Study on Procedural Document QA [52.557503571760215]
  We argue that clearer assessments of risks and harms to users will be possible when we specialize the analysis to more concrete applications and their plausible users. We conduct a risk-oriented error analysis that could then inform the design of a future system to be deployed with lower risk of harm and better performance.
  arXiv  Detail & Related papers  (2024-08-16T17:23:43Z)
• 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. Foundation models as the "brain" of EAI agents for high-level task planning have shown promising results. However, the deployment of these agents in physical environments presents significant safety challenges. This study introduces EARBench, a novel framework for automated physical risk assessment in EAI scenarios.
  arXiv  Detail & Related papers  (2024-08-08T13:19:37Z)
• Near to Mid-term Risks and Opportunities of Open-Source Generative AI [94.06233419171016]
  Applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic changes has triggered a lively debate about potential risks and resulted in calls for tighter regulation. This regulation is likely to put at risk the budding field of open-source Generative AI.
  arXiv  Detail & Related papers  (2024-04-25T21:14:24Z)
• Adversarial AI in Insurance: Pervasiveness and Resilience [0.0]
  We study Adversarial Attacks, which consist of the creation of modified input data to deceive an AI system and produce false outputs. We argue on defence methods and precautionary systems, considering that they can involve few-shot and zero-shot multilabelling. A related topic, with growing interest, is the validation and verification of systems incorporating AI and ML components.
  arXiv  Detail & Related papers  (2023-01-17T08:49:54Z)
• A taxonomic system for failure cause analysis of open source AI incidents [6.85316573653194]
  This work demonstrates how to apply expert knowledge on the population of incidents in the AI Incident Database (AIID) to infer potential and likely technical causative factors that contribute to reported failures and harms. We present early work on a taxonomic system that covers a cascade of interrelated incident factors, from system goals (nearly always known) to methods / technologies (knowable in many cases) and technical failure causes (subject to expert analysis) of the implicated systems.
  arXiv  Detail & Related papers  (2022-11-14T11:21:30Z)
• Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database [6.85316573653194]
  The AI Incident Database is an incident collection initiated by an industrial/non-profit cooperative to enable AI incident avoidance and mitigation. The database supports a variety of research and development use cases with faceted and full text search on more than 1,000 incident reports archived to date.
  arXiv  Detail & Related papers  (2020-11-17T08:55:14Z)
• Bias in Multimodal AI: Testbed for Fair Automatic Recruitment [73.85525896663371]
  We study how current multimodal algorithms based on heterogeneous sources of information are affected by sensitive elements and inner biases in the data. We train automatic recruitment algorithms using a set of multimodal synthetic profiles consciously scored with gender and racial biases. Our methodology and results show how to generate fairer AI-based tools in general, and in particular fairer automated recruitment systems.
  arXiv  Detail & Related papers  (2020-04-15T15:58:05Z)
• On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems [62.997667081978825]
  We present a formal framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. The first class involves adversarial examples and concerns the introduction of small perturbations of the input data that cause misclassification. The second class, introduced here for the first time and named stealth attacks, involves small perturbations to the AI system itself.
  arXiv  Detail & Related papers  (2020-04-09T10:56:53Z)

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.