Federated Learning (FL) offers a promising approach for collaborative model training in healthcare while preserving data privacy. However, existing FL methods often fall short in addressing two critical challenges: client-level fairness and compounded uncertainty from data heterogeneity and privacy-preserving mechanisms. We propose fair-LDP, a fairness-aware Local Differential Privacy framework that promotes fairness and privacy via uncertainty-guided aggregation in federated healthcare AI. fair-LDP leverages evidential neural networks (ENNs) to quantify predictive uncertainty and introduces a novel strategy that uses uncertainty-driven local differential privacy to guide fairness-aware updates while preserving data privacy. This ensures equitable performance across clients with varying data quality while mitigating the influence of unreliable or outlier updates. fair-LDP incorporates an adaptive mechanism that adjusts each client's privacy budget based on model performance, balancing fairness, privacy, and accuracy. We evaluate fair-LDP on real-world healthcare datasets under both IID and non-IID settings. Our experimental results show that it consistently outperforms state-of-the-art fairness-aware and privacy-preserving FL baselines, with no added computational overhead, while maintaining privacy guarantees comparable to homomorphic encryption and secure multiparty computation. By integrating uncertainty modeling, fairness-aware aggregation, and adaptive local differential privacy, fair-LDP provides a practical and principled solution for responsible, equitable, and privacy-preserving federated learning in healthcare.

As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often simplistic, allowing models to perform uniformly well and making it difficult to distinguish their capabilities. Additionally, benchmarks typically rely on static question-answer pairs that the models might memorize or guess. To address these limitations, we introduce Dynamic Intelligence Assessment (DIA), a novel methodology for testing AI models using dynamic question templates and improved metrics across multiple disciplines such as mathematics, cryptography, cybersecurity, and computer science. The accompanying dataset, DIA-Bench, contains a diverse collection of challenge templates with mutable parameters presented in various formats, including text, PDFs, compiled binaries, visual puzzles, and CTF-style cybersecurity challenges. Our framework introduces four new metrics to assess a model’s reliability and confidence across multiple attempts. These metrics revealed that even simple questions are frequently answered incorrectly when posed in varying forms, highlighting significant gaps in models’ reliability. Notably, API models like GPT-4o often overestimated their mathematical capabilities, while ChatGPT-4o demonstrated better performance due to effective tool usage. In self-assessment OpenAI’s o1-mini proved to have the best judgement on what tasks it should attempt to solve. We evaluated 25 state-of-the-art LLMs using DIA-Bench, showing that current models struggle with complex tasks and often display unexpectedly low confidence, even with simpler questions. The DIA framework sets a new standard for assessing not only problem-solving, but also a model’s adaptive intelligence and ability to assess its limitations. The dataset is publicly available on the project’s page: https://github.com/DIA-Bench.

The Competitive Influence Maximization (CIM) problem involves entities competing to maximize influence in online social networks (OSNs). While Deep Reinforcement Learning (DRL) methods have shown promise, most assume binary user opinions and overlook behavioral factors. We introduce DRIM, a novel DRL-based CIM framework using Subjective Logic (SL) to incorporate user preferences and uncertainty, optimizing seed selection to spread true information while countering false information. DRIM’s Uncertainty-based Opinion Model (UOM) provides a realistic representation of user opinions. Results demonstrate that UOM maintains over 80% true influence against advanced misinformation, and DRIM outperforms state-of-the-art methods by up to 45% in influence and 77% in speed. DRIM also excels in limited-resource scenarios, networks with 10% invisibility, and when users are inclined to doubt true information.

This paper presents PSO, an ontological framework and a methodology for improving physical security and insider threat detection. PSO can facilitate forensic data analysis and proactively mitigate insider threats by leveraging rule-based anomaly detection. In all too many cases, rule-based anomaly detection can detect employee deviations from organizational security policies. In addition, PSO can be considered a security provenance solution because of its ability to fully reconstruct attack patterns. Provenance graphs can be further analyzed to identify deceptive actions and overcome analytical mistakes that can result in bad decision-making, such as false attribution. Moreover, the information can be used to enrich the available intelligence (about intrusion attempts) that can form use cases to detect and remediate limitations in the system, such as loosely-coupled provenance graphs that in many cases indicate weaknesses in the physical security architecture. Ultimately, validation of the framework through use cases demonstrates and proves that PS0 can improve an organization's security posture in terms of physical security and insider threat detection.

An Abstract Argumentation Framework (AAF) is an abstract structure consisting of a set arguments, whose origin, nature, and possible internal organisation is not specified, and by a binary relation of attack on the set of arguments, whose meaning is not specified either. Subjective logic provides a standard set of logical operators, intended for use in domains containing uncertainty. In this paper, we define an extension of AAFs in which each argument and attacks is evaluated with an opinion, by revisiting the constellations approach developed for probabilistic AAFs. In this way, different agents can merge their opinions on how much arguments and attacks are “trustworthy”, e.g., they do not represent fallacies or enthymemes. Finally, subjective logic operators can be used to fuse the belief of different possible worlds (i.e., a constellation of sub-graphs in the original AAF) containing different arguments and attacks.

In this work, we study different types of uncertainty in subjective opinions based on the internal belief mass distribution and the base rate distribution. Subjective opinions which are used as arguments in subjective logic (SL) expand the traditional belief functions by including base rate distributions. Fundamental uncertainty characteristics of a given opinion depend on its `singularity', `vagueness', `vacuity', `dissonance', `consonance' and `monosonance'. We define those concepts in the formalism of SL and show how these characteristics can be manifested in the three different opinion classes which are binomial, multinomial, and hyper-opinions. We clarify the relationships between the uncertainty characteristics and discuss how they influence decision making in SL.

Belief fusion consists of taking into account multiple sources of belief about a domain of interest. This paper describes cumulative and averaging multi-source belief fusion in the formalism of subjective logic, which represent generalisations of binary-source belief fusion operators previously described. The advantage of this approach is that we can model and analyse belief fusion situations involving an arbitrary number of sources.

Different belief sources often provide conflicting evidence, due to e.g. varying source reliability or deliberate deception. Source trust expresses the source reliability as seen by the analyst. In case of conflicting sources the analyst needs a strategy for managing and revising source trust. Intuitively, trust should be reduced for sources that produce advice which is in conflict with the ground truth, or in conflict with the advice from other highly trusted sources. The present paper uses the formalism of subjective logic to describe strategies for source trust revision according to this principle.

Many websites presently provide the facility for users to rate items quality based on user opinion. These ratings are used later to produce item reputation scores. The majority of websites apply the mean method to aggregate user ratings. This method is very simple and is not considered as an accurate aggregator. Many methods have been proposed to make aggregators produce more accurate reputation scores. In the majority of proposed methods the authors use extra information about the rating providers or about the context (e.g. time) in which the rating was given. However, this information is not available all the time. In such cases these methods produce reputation scores using the mean method or other alternative simple methods. In this paper, we propose a novel reputation model that generates more accurate item reputation scores based on collected ratings only. Our proposed model embeds statistical data, previously disregarded, of a given rating dataset in order to enhance the accuracy of the generated reputation scores. In more detail, we use the Beta distribution to produce weights for ratings and aggregate ratings using the weighted mean method. Experiments show that the proposed model exhibits performance superior to that of current state-of-the-art models.