In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI

• URL: http://arxiv.org/abs/2503.16861v1
• Date: Fri, 21 Mar 2025 05:09:46 GMT
• Title: In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI
• Authors: Shayne Longpre, Kevin Klyman, Ruth E. Appel, Sayash Kapoor, Rishi Bommasani, Michelle Sahar, Sean McGregor, Avijit Ghosh, Borhane Blili-Hamelin, Nathan Butters, Alondra Nelson, Amit Elazari, Andrew Sellars, Casey John Ellis, Dane Sherrets, Dawn Song, Harley Geiger, Ilona Cohen, Lauren McIlvenny, Madhulika Srikumar, Mark M. Jaycox, Markus Anderljung, Nadine Farid Johnson, Nicholas Carlini, Nicolas Miailhe, Nik Marda, Peter Henderson, Rebecca S. Portnoff, Rebecca Weiss, Victoria Westerhoff, Yacine Jernite, Rumman Chowdhury, Percy Liang, Arvind Narayanan,
• Abstract summary: We call for three interventions to advance system safety.<n>First, we propose using standardized AI flaw reports and rules of engagement for researchers.<n>Second, we propose GPAI system providers adopt broadly-scoped flaw disclosure programs.<n>Third, we advocate for the development of improved infrastructure to coordinate distribution of flaw reports.
• Score: 93.33036653316591
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The widespread deployment of general-purpose AI (GPAI) systems introduces significant new risks. Yet the infrastructure, practices, and norms for reporting flaws in GPAI systems remain seriously underdeveloped, lagging far behind more established fields like software security. Based on a collaboration between experts from the fields of software security, machine learning, law, social science, and policy, we identify key gaps in the evaluation and reporting of flaws in GPAI systems. We call for three interventions to advance system safety. First, we propose using standardized AI flaw reports and rules of engagement for researchers in order to ease the process of submitting, reproducing, and triaging flaws in GPAI systems. Second, we propose GPAI system providers adopt broadly-scoped flaw disclosure programs, borrowing from bug bounties, with legal safe harbors to protect researchers. Third, we advocate for the development of improved infrastructure to coordinate distribution of flaw reports across the many stakeholders who may be impacted. These interventions are increasingly urgent, as evidenced by the prevalence of jailbreaks and other flaws that can transfer across different providers' GPAI systems. By promoting robust reporting and coordination in the AI ecosystem, these proposals could significantly improve the safety, security, and accountability of GPAI systems.

Related papers

• AI threats to national security can be countered through an incident regime [55.2480439325792]
  We propose a legally mandated post-deployment AI incident regime that aims to counter potential national security threats from AI systems. Our proposed AI incident regime is split into three phases. The first phase revolves around a novel operationalization of what counts as an 'AI incident' The second and third phases spell out that AI providers should notify a government agency about incidents, and that the government agency should be involved in amending AI providers' security and safety procedures.
  arXiv  Detail & Related papers  (2025-03-25T17:51:50Z)
• Compliance of AI Systems [0.0]
  This paper systematically examines the compliance of AI systems with relevant legislation, focusing on the EU's AI Act.<n>The analysis highlighted many challenges associated with edge devices, which are increasingly being used to deploy AI applications closer and closer to the data sources.<n>The importance of data set compliance is highlighted as a cornerstone for ensuring the trustworthiness, transparency, and explainability of AI systems.
  arXiv  Detail & Related papers  (2025-03-07T16:53:36Z)
• Enabling External Scrutiny of AI Systems with Privacy-Enhancing Technologies [0.0]
  This article describes how technical infrastructure developed by the nonprofit OpenMined enables external scrutiny of AI systems without compromising sensitive information.<n>In practice, external researchers have struggled to gain access to AI systems because of AI companies' legitimate concerns about security, privacy, and intellectual property.<n>PETs have reached a new level of maturity: end-to-end technical infrastructure developed by OpenMined combines several PETs into various setups that enable privacy-preserving audits of AI systems.
  arXiv  Detail & Related papers  (2025-02-05T15:31:11Z)
• Position: A taxonomy for reporting and describing AI security incidents [57.98317583163334]
  We argue that specific are required to describe and report security incidents of AI systems.<n>Existing frameworks for either non-AI security or generic AI safety incident reporting are insufficient to capture the specific properties of AI security.
  arXiv  Detail & Related papers  (2024-12-19T13:50:26Z)
• Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems [88.80306881112313]
  We will introduce and define a family of approaches to AI safety, which we will refer to as guaranteed safe (GS) AI. The core feature of these approaches is that they aim to produce AI systems which are equipped with high-assurance quantitative safety guarantees. We outline a number of approaches for creating each of these three core components, describe the main technical challenges, and suggest a number of potential solutions to them.
  arXiv  Detail & Related papers  (2024-05-10T17:38:32Z)
• The risks of risk-based AI regulation: taking liability seriously [46.90451304069951]
  The development and regulation of AI seems to have reached a critical stage. Some experts are calling for a moratorium on the training of AI systems more powerful than GPT-4. This paper analyses the most advanced legal proposal, the European Union's AI Act.
  arXiv  Detail & Related papers  (2023-11-03T12:51:37Z)
• Towards an AI Accountability Policy [16.59829043755575]
  We examine how high-risk technologies have been successfully regulated at the national level.<n>We propose a tiered system of explainability and benchmarking requirements for commercial AI systems.
  arXiv  Detail & Related papers  (2023-07-25T17:09:28Z)
• Trustworthy AI Inference Systems: An Industry Research View [58.000323504158054]
  We provide an industry research view for approaching the design, deployment, and operation of trustworthy AI inference systems. We highlight opportunities and challenges in AI systems using trusted execution environments. We outline areas of further development that require the global collective attention of industry, academia, and government researchers.
  arXiv  Detail & Related papers  (2020-08-10T23:05:55Z)
• Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims [59.64274607533249]
  AI developers need to make verifiable claims to which they can be held accountable. This report suggests various steps that different stakeholders can take to improve the verifiability of claims made about AI systems. We analyze ten mechanisms for this purpose--spanning institutions, software, and hardware--and make recommendations aimed at implementing, exploring, or improving those mechanisms.
  arXiv  Detail & Related papers  (2020-04-15T17:15:35Z)

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.