相关论文: Robust ML Auditing using Prior Knowledge

Algorithmic discrimination is a critical concern as machine learning models are used in high-stakes decision-making in legally protected contexts. Although substantial research on algorithmic bias and discrimination has led to the…

The rapid advancement of AI systems has raised widespread concerns about potential harms of frontier AI systems and the need for responsible evaluation and oversight. In this position paper, we argue that frontier AI companies should report…

Public attention towards explainability of artificial intelligence (AI) systems has been rising in recent years to offer methodologies for human oversight. This has translated into the proliferation of research outputs, such as from…

Automated decision systems are increasingly used for consequential decision making -- for a variety of reasons. These systems often rely on sophisticated yet opaque models, which do not (or hardly) allow for understanding how or why a given…

There's a long tradition of research using computational intelligence (methods from artificial intelligence (AI) and machine learning (ML)), to automatically discover, implement, and fine-tune strategies for autonomous adaptive automated…

There is substantial evidence that Artificial Intelligence (AI) and Machine Learning (ML) algorithms can generate bias against minorities, women, and other protected classes. Federal and state laws have been enacted to protect consumers…

Fervent calls for more robust governance of the harms associated with artificial intelligence (AI) are leading to the adoption around the world of what regulatory scholars have called a management-based approach to regulation. Recent…

The lack of ground truth explanation labels is a fundamental challenge for quantitative evaluation in explainable artificial intelligence (XAI). This challenge becomes especially problematic when evaluation methods have numerous…

Privacy-preserving AI algorithms are widely adopted in various domains, but the lack of transparency might pose accountability issues. While auditing algorithms can address this issue, machine-based audit approaches are often costly and…

The European legislature has proposed the Digital Services Act (DSA) and Artificial Intelligence Act (AIA) to regulate platforms and Artificial Intelligence (AI) products. We review to what extent third-party audits are part of both laws…

Advances in AI agent capabilities have outpaced users' ability to meaningfully oversee their execution. AI agents can perform sophisticated, multi-step knowledge work autonomously from start to finish, yet this process remains effectively…

The rapid progress in Large Language Models (LLMs) could transform many fields, but their fast development creates significant challenges for oversight, ethical creation, and building user trust. This comprehensive review looks at key trust…

AI companies increasingly develop and deploy privacy-enhancing technologies, bias-constraining measures, evaluation frameworks, and alignment techniques -- framing them as addressing concerns related to data privacy, algorithmic fairness,…

This article describes how technical infrastructure developed by the nonprofit OpenMined enables external scrutiny of AI systems without compromising sensitive information. Independent external scrutiny of AI systems provides crucial…

While high-stakes ML applications demand strict regulations, strategic ML providers often evade them to lower development costs. To address this challenge, we cast AI regulation as a mechanism design problem under uncertainty and introduce…

Should firms that apply machine learning algorithms in their decision-making make their algorithms transparent to the users they affect? Despite growing calls for algorithmic transparency, most firms have kept their algorithms opaque,…

Reliable explainability is not only a technical goal but also a cornerstone of private AI governance. As AI models enter high-stakes sectors, private actors such as auditors, insurers, certification bodies, and procurement agencies require…

Many practical learning systems aggregate data across many users, while learning theory traditionally considers a single learner who trusts all of their observations. A case in point is the foundational learning problem of prediction with…

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…

To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some…