Related papers: On the Foundations of Trustworthy Artificial Intel…

AI memory systems are evolving toward unified context layers that enable efficient cross-agent collaboration and multi-tool workflows, facilitating better accumulation of personal data and learning of user preferences. However,…

Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces). Yet ML-as-a-Service reveals little about what actually ran or whether returned outputs faithfully reflect the intended inputs.…

Trustworthiness in neural networks is crucial for their deployment in critical applications, where reliability, confidence, and uncertainty play pivotal roles in decision-making. Traditional performance metrics such as accuracy and…

The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including…

In this paper we focus on the problem of assigning uncertainties to single-point predictions generated by a deterministic model that outputs a continuous variable. This problem applies to any state-of-the-art physics or engineering models…

The ability to produce random numbers that are unknown to any outside party is crucial for many applications. Device-independent randomness generation does not require trusted devices and therefore provides strong guarantees of the security…

We present an overview of the literature on trust in AI and AI trustworthiness and argue for the need to distinguish these concepts more clearly and to gather more empirically evidence on what contributes to people s trusting behaviours. We…

This paper reviews Trustworthy Artificial Intelligence (TAI) and its various definitions. Considering the principles respected in any society, TAI is often characterized by a few attributes, some of which have led to confusion in regulatory…

To create usable and deployable Artificial Intelligence (AI) systems, there requires a level of assurance in performance under many different conditions. Many times, deployed machine learning systems will require more classic logic and…

Organizational knowledge used by AI agents typically lacks epistemic structure: retrieval systems surface semantically relevant content without distinguishing binding decisions from abandoned hypotheses, contested claims from settled ones,…

This position paper argues that standardized item-level benchmark data should become the default infrastructure for AI evaluation. Current evaluations suffer from underspecified item selection, construct misalignment, and poor…

We develop deterministic algorithms for the problems of consensus, gossiping and checkpointing with nodes prone to failing. Distributed systems are modeled as synchronous complete networks. Failures are represented either as crashes or…

Certified randomness guaranteed to be unpredictable by adversaries is central to information security. The fundamental randomness inherent in quantum physics makes certification possible from devices that are only weakly characterised, i.e.…

In this paper we argue that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. As an illustrating example we focus on uncertainty quantification in the context of counterfactual…

This workshop Report Out focuses on the foundational elements of trustworthy AI and OR technology, and how to ensure all AI and OR systems implement these elements in their system designs. Four sessions on various topics within Trustworthy…

A fundamental problem in data fusion is to determine the veracity of multi-source data in order to resolve conflicts. While previous work in truth discovery has proved to be useful in practice for specific settings, sources' behavior or…

The AI act is the European Union-wide regulation of AI systems. It includes specific provisions for general-purpose AI models which however need to be further interpreted in terms of technical standards and state-of-art studies to ensure…

Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…

In certain approaches to quantum computing the operations between qubits are non-deterministic and likely to fail. For example, a distributed quantum processor would achieve scalability by networking together many small components;…

Rising concern for the societal implications of artificial intelligence systems has inspired a wave of academic and journalistic literature in which deployed systems are audited for harm by investigators from outside the organizations…