Related papers: NeurIPS Should Require Reproducibility Standards f…
Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general capability evaluations are widespread, social impact…
As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence about system capabilities and risks. Yet there remains a…
This article argues that frontier artificial intelligence (AI) developers need an internal audit function. First, it describes the role of internal audit in corporate governance: internal audit evaluates the adequacy and effectiveness of a…
Generative models must ensure both privacy and fairness for Trustworthy AI. While these goals have been pursued separately, recent studies propose to combine existing privacy and fairness techniques to achieve both goals. However, naively…
Fairness has become increasingly pivotal in medical image recognition. However, without mitigating bias, deploying unfair medical AI systems could harm the interests of underprivileged populations. In this paper, we observe that while…
An AI design framework was developed based on three core principles, namely understandability, trust, and usability. The framework was conceptualized by synthesizing evidence from the literature and by consulting with experts. The initial…
AI systems face a growing number of AI security threats that are increasingly exploited in the real world. Hence, shared AI incident reporting practices are emerging in industry as best practice and as mandated by regulatory requirements.…
As AI systems integrate into critical infrastructure, security gaps in AI compliance frameworks demand urgent attention. This paper audits and quantifies security risks in three major AI governance standards: NIST AI RMF 1.0, UK's AI and…
Numerous AI ethics checklists and frameworks have been proposed focusing on different dimensions of ethical AI such as fairness, explainability, and safety. Yet, no such work has been done on developing transparent AI systems for real-world…
The field of deep learning has witnessed significant breakthroughs, spanning various applications, and fundamentally transforming current software capabilities. However, alongside these advancements, there have been increasing concerns…
The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…
Decisions made by various Artificial Intelligence (AI) systems greatly influence our day-to-day lives. With the increasing use of AI systems, it becomes crucial to know that they are fair, identify the underlying biases in their…
The history of science and technology shows that seemingly innocuous developments in scientific theories and research have enabled real-world applications with significant negative consequences for humanity. In order to ensure that the…
The rapid integration of AI into education has prioritized capability over trustworthiness, creating significant risks. Real-world deployments reveal that even advanced models are insufficient without extensive architectural scaffolding to…
Attribution methods compute importance scores for input features to explain model predictions. However, assessing the faithfulness of these methods remains challenging due to the absence of attribution ground truth to model predictions. In…
Recent advances in machine learning, particularly the emergence of foundation models, are leading to new opportunities to develop technology-based solutions to societal problems. However, the reasoning and inner workings of today's complex…
The EU Artificial Intelligence (AI) Act directs businesses to assess their AI systems to ensure they are developed in a way that is human-centered and trustworthy. The rapid adoption of AI in the industry has outpaced ethical evaluation…
Responsible disclosure limitation is an iterative exercise in risk assessment and mitigation. From time to time, as disclosure risks grow and evolve and as data users' needs change, agencies must consider redesigning the disclosure…
We propose new tools for policy-makers to use when assessing and correcting fairness and bias in AI algorithms. The three tools are: - A new definition of fairness called "controlled fairness" with respect to choices of protected features…
We introduce the AI Security Pyramid of Pain, a framework that adapts the cybersecurity Pyramid of Pain to categorize and prioritize AI-specific threats. This framework provides a structured approach to understanding and addressing various…