Related papers: Foundations of a Time-Consistent Counterfactual Ac…
We introduce AI Runtime Infrastructure, a distinct execution-time layer that operates above the model and below the application, actively observing, reasoning over, and intervening in agent behavior to optimize task success, latency, token…
Counterfactual explanations have emerged as a prominent method in Explainable Artificial Intelligence (XAI), providing intuitive and actionable insights into Machine Learning model decisions. In contrast to other traditional feature…
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…
We adapt split conformal prediction and adaptive conformal inference (ACI) to continuous AI agent evaluation, providing distribution-free coverage guarantees for forecasted quality scores. Conformal intervals achieve calibration error below…
Artificial currencies have grown in popularity in many real-world resource allocation settings, gaining traction in government benefits programs like food assistance and transit benefits programs. However, such programs are susceptible to…
We evaluate the autonomous cyber-attack capabilities of frontier AI models on two purpose-built cyber ranges-a 32-step corporate network attack and a 7-step industrial control system attack-that require chaining heterogeneous capabilities…
Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics, is especially…
This paper develops a control-theoretic framework for analyzing agentic systems embedded within feedback control loops, where an AI agent may adapt controller parameters, select among control strategies, invoke external tools, reconfigure…
To counter fragmented, high-risk adoption of commercial AI tools, we built and ran an institutional AI platform in a six-month, 300-user pilot, showing that a university of applied sciences can offer advanced AI with fair access,…
Autonomous multi-agent systems (MAS) are useful for automating complex tasks but raise trust concerns due to risks such as miscoordination or goal misalignment. Explainability is vital for users' trust calibration, but explainable MAS face…
Explaining the predictions of a deep neural network is a nontrivial task, yet high-quality explanations for predictions are often a prerequisite for practitioners to trust these models. Counterfactual explanations aim to explain predictions…
Frontier AI Safety Policies concentrate on prevention: capability evaluations, deployment gates, and usage constraints, while neglecting the capacity to coordinate responses when prevention fails. We argue this coordination gap is…
We consider after-study statistical inference for sequentially designed experiments wherein multiple units are assigned treatments for multiple time points using treatment policies that adapt over time. Our goal is to provide inference…
Before deploying an AI system to replace an existing process, it must be compared with the incumbent to ensure improvement without added risk. Traditional evaluation relies on ground truth for both systems, but this is often unavailable due…
The impact of frontier AI (i.e., AI agents and foundation models) in cybersecurity is rapidly increasing. In this paper, we comprehensively analyze this trend through multiple aspects: quantitative benchmarks, qualitative literature review,…
Agent frameworks increasingly encode tool-using behavior as explicit workflow graphs, yet safety enforcement remains a runtime concern. These frameworks expose analyzable graph structure through their APIs, enabling pre-deployment static…
The rapid proliferation of artificial intelligence (AI) has exposed significant deficiencies in risk governance. While ex-ante harm identification and prevention have advanced, Responsible AI scholarship remains underdeveloped in addressing…
Explainable Artificial Intelligence (XAI) is a set of techniques that allows the understanding of both technical and non-technical aspects of Artificial Intelligence (AI) systems. XAI is crucial to help satisfying the increasingly important…
The rapid expansion of AI-driven applications powered by large language models has led to a surge in AI interaction data, raising urgent challenges in security, accountability, and risk traceability. This paper presents AiAuditTrack (AAT),…
Assessing the safety of autonomous driving (AD) systems against security threats, particularly backdoor attacks, is a stepping stone for real-world deployment. However, existing works mainly focus on pixel-level triggers that are…