Federico Cerutti

Marco Cominelli, Francesco Gringoli, Lance M. Kaplan et al.

Wi-Fi devices can effectively be used as passive radar systems that sense what happens in the surroundings and can even discern human activity. We propose, for the first time, a principled architecture which employs Variational Auto-Encoders for estimating a latent distribution responsible for generating the data, and Evidential Deep Learning for its ability to sense out-of-distribution activities. We verify that the fused data processed by different antennas of the same Wi-Fi receiver results in increased accuracy of human activity recognition compared with the most recent benchmarks, while still being informative when facing out-of-distribution samples and enabling semantic interpretation of latent variables in terms of physical phenomena. The results of this paper are a first contribution toward the ultimate goal of providing a flexible, semantic characterisation of black-swan events, i.e., events for which we have limited to no training data.

Rodolfo Valentim, Idilio Drago, Marco Mellia et al.

Sound-squatting is a phishing attack that tricks users into malicious resources by exploiting similarities in the pronunciation of words. Proactive defense against sound-squatting candidates is complex, and existing solutions rely on manually curated lists of homophones. We here introduce Sound-skwatter, a multi-language AI-based system that generates sound-squatting candidates for proactive defense. Sound-skwatter relies on an innovative multi-modal combination of Transformers Networks and acoustic models to learn sound similarities. We show that Sound-skwatter can automatically list known homophones and thousands of high-quality candidates. In addition, it covers cross-language sound-squatting, i.e., when the reader and the listener speak different languages, supporting any combination of languages. We apply Sound-skwatter to network-centric phishing via squatted domain names. We find ~ 10% of the generated domains exist in the wild, the vast majority unknown to protection solutions. Next, we show attacks on the PyPI package manager, where ~ 17% of the popular packages have at least one existing candidate. We believe Sound-skwatter is a crucial asset to mitigate the sound-squatting phenomenon proactively on the Internet. To increase its impact, we publish an online demo and release our models and code as open source.

Conrad D. Hougen, Lance M. Kaplan, Magdalena Ivanovska et al.

In second-order uncertain Bayesian networks, the conditional probabilities are only known within distributions, i.e., probabilities over probabilities. The delta-method has been applied to extend exact first-order inference methods to propagate both means and variances through sum-product networks derived from Bayesian networks, thereby characterizing epistemic uncertainty, or the uncertainty in the model itself. Alternatively, second-order belief propagation has been demonstrated for polytrees but not for general directed acyclic graph structures. In this work, we extend Loopy Belief Propagation to the setting of second-order Bayesian networks, giving rise to Second-Order Loopy Belief Propagation (SOLBP). For second-order Bayesian networks, SOLBP generates inferences consistent with those generated by sum-product networks, while being more computationally efficient and scalable.

Conrad D. Hougen, Lance M. Kaplan, Federico Cerutti et al.

When the historical data are limited, the conditional probabilities associated with the nodes of Bayesian networks are uncertain and can be empirically estimated. Second order estimation methods provide a framework for both estimating the probabilities and quantifying the uncertainty in these estimates. We refer to these cases as uncer tain or second-order Bayesian networks. When such data are complete, i.e., all variable values are observed for each instantiation, the conditional probabilities are known to be Dirichlet-distributed. This paper improves the current state-of-the-art approaches for handling uncertain Bayesian networks by enabling them to learn distributions for their parameters, i.e., conditional probabilities, with incomplete data. We extensively evaluate various methods to learn the posterior of the parameters through the desired and empirically derived strength of confidence bounds for various queries.

Cai Davies, Marc Roig Vilamala, Alun D. Preece et al.

This work reveals an evidential signal that emerges from the uncertainty value in Evidential Deep Learning (EDL). EDL is one example of a class of uncertainty-aware deep learning approaches designed to provide confidence (or epistemic uncertainty) about the current test sample. In particular for computer vision and bidirectional encoder large language models, the `evidential signal' arising from the Dirichlet strength in EDL can, in some cases, discriminate between classes, which is particularly strong when using large language models. We hypothesise that the KL regularisation term causes EDL to couple aleatoric and epistemic uncertainty. In this paper, we empirically investigate the correlations between misclassification and evaluated uncertainty, and show that EDL's `evidential signal' is due to misclassification bias. We critically evaluate EDL with other Dirichlet-based approaches, namely Generative Evidential Neural Networks (EDL-GEN) and Prior Networks, and show theoretically and empirically the differences between these loss functions. We conclude that EDL's coupling of uncertainty arises from these differences due to the use (or lack) of out-of-distribution samples during training.

Marco Cominelli, Francesco Gringoli, Lance M. Kaplan et al.

Wi-Fi devices, akin to passive radars, can discern human activities within indoor settings due to the human body's interaction with electromagnetic signals. Current Wi-Fi sensing applications predominantly employ data-driven learning techniques to associate the fluctuations in the physical properties of the communication channel with the human activity causing them. However, these techniques often lack the desired flexibility and transparency. This paper introduces DeepProbHAR, a neuro-symbolic architecture for Wi-Fi sensing, providing initial evidence that Wi-Fi signals can differentiate between simple movements, such as leg or arm movements, which are integral to human activities like running or walking. The neuro-symbolic approach affords gathering such evidence without needing additional specialised data collection or labelling. The training of DeepProbHAR is facilitated by declarative domain knowledge obtained from a camera feed and by fusing signals from various antennas of the Wi-Fi receivers. DeepProbHAR achieves results comparable to the state-of-the-art in human activity recognition. Moreover, as a by-product of the learning process, DeepProbHAR generates specialised classifiers for simple movements that match the accuracy of models trained on finely labelled datasets, which would be particularly costly.

Pietro Baroni, Federico Cerutti, Massimiliano Giacomin et al.

The sixth assessment of the international panel on climate change (IPCC) states that "cumulative net CO2 emissions over the last decade (2010-2019) are about the same size as the 11 remaining carbon budget likely to limit warming to 1.5C (medium confidence)." Such reports directly feed the public discourse, but nuances such as the degree of belief and of confidence are often lost. In this paper, we propose a formal account for allowing such degrees of belief and the associated confidence to be used to label arguments in abstract argumentation settings. Differently from other proposals in probabilistic argumentation, we focus on the task of probabilistic inference over a chosen query building upon Sato's distribution semantics which has been already shown to encompass a variety of cases including the semantics of Bayesian networks. Borrowing from the vast literature on such semantics, we examine how such tasks can be dealt with in practice when considering uncertain probabilities, and discuss the connections with existing proposals for probabilistic argumentation.

Olaf Lipinski, Adam J. Sobey, Federico Cerutti et al.

Emergent communication studies the development of language between autonomous agents, aiming to improve understanding of natural language evolution and increase communication efficiency. While temporal aspects of language have been considered in computational linguistics, there has been no research on temporal references in emergent communication. This paper addresses this gap, by exploring how agents communicate about temporal relationships. We analyse three potential influences for the emergence of temporal references: environmental, external, and architectural changes. Our experiments demonstrate that altering the loss function is insufficient for temporal references to emerge; rather, architectural changes are necessary. However, a minimal change in agent architecture, using a different batching method, allows the emergence of temporal references. This modified design is compared with the standard architecture in a temporal referential games environment, which emphasises temporal relationships. The analysis indicates that over 95\% of the agents with the modified batching method develop temporal references, without changes to their loss function. We consider temporal referencing necessary for future improvements to the agents' communication efficiency, yielding a closer to optimal coding as compared to purely compositional languages. Our readily transferable architectural insights provide the basis for their incorporation into other emergent communication settings.

Roko Parac, Lorenzo Nodari, Leo Ardon et al.

This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state machine that decomposes the agent's task into different subtasks. PROB-IRM uses a state-of-the-art inductive logic programming framework robust to noisy examples to learn RMs from noisy traces using the Bayesian posterior degree of beliefs, thus ensuring robustness against inconsistencies. Pivotal for the results is the interleaving between RM learning and policy learning: a new RM is learned whenever the RL agent generates a trace that is believed not to be accepted by the current RM. To speed up the training of the RL agent, PROB-IRM employs a probabilistic formulation of reward shaping that uses the posterior Bayesian beliefs derived from the traces. Our experimental analysis shows that PROB-IRM can learn (potentially imperfect) RMs from noisy traces and exploit them to train an RL agent to solve its tasks successfully. Despite the complexity of learning the RM from noisy traces, agents trained with PROB-IRM perform comparably to agents provided with handcrafted RMs.

Alessandro Pagani, Marco Cominelli, Liying Han et al.

This paper presents a preliminary analysis of the ability of Chronos foundation model to process and internally represent frequency domain information. Foundation models that process time-series data offer practitioners a unified architecture capable of learning generic temporal representations across diverse tasks and domains, reducing the need for task-specific feature engineering and enabling transfer across signal modalities. Despite their growing adoption, the extent to which such models encode fundamental signal properties remains insufficiently characterised. We address this gap by analysing Chronos under controlled conditions, starting from the simplest class of signals: discrete sinusoids generated at fixed frequencies. Using lightweight online minimum description length probes applied to the decoder architecture, we test for the presence and separability of frequency information in the model's internal representations. The results provide insight into how frequential content is captured across the frequency spectrum and highlight regimes in which representation quality may degrade or require particular care. These findings offer practical guidance for users of Chronos in signal processing and information fusion contexts, and contribute to ongoing efforts to improve the interpretability and evaluation of foundation models for temporal data.

John Birkbeck, Adam Sobey, Federico Cerutti et al.

Reinforcement learning (RL) agents are costly to train and fragile to environmental changes. They often perform poorly when there are many changing tasks, prohibiting their widespread deployment in the real world. Many Lifelong RL agent designs have been proposed to mitigate issues such as catastrophic forgetting or demonstrate positive characteristics like forward transfer when change occurs. However, no prior work has established whether the impact on agent performance can be predicted from the change itself. Understanding this relationship will help agents proactively mitigate a change's impact for improved learning performance. We propose Change-Induced Regret Proxy (CHIRP) metrics to link change to agent performance drops and use two environments to demonstrate a CHIRP's utility in lifelong learning. A simple CHIRP-based agent achieved $48\%$ higher performance than the next best method in one benchmark and attained the best success rates in 8 of 10 tasks in a second benchmark which proved difficult for existing lifelong RL agents.

Lorenzo Nodari, Federico Cerutti

Robustness to noise is of utmost importance in reinforcement learning systems, particularly in military contexts where high stakes and uncertain environments prevail. Noise and uncertainty are inherent features of military operations, arising from factors such as incomplete information, adversarial actions, or unpredictable battlefield conditions. In RL, noise can critically impact decision-making, mission success, and the safety of personnel. Reward machines offer a powerful tool to express complex reward structures in RL tasks, enabling the design of tailored reinforcement signals that align with mission objectives. This paper considers the problem of the robustness of intelligence-driven reinforcement learning based on reward machines. The preliminary results presented suggest the need for further research in evidential reasoning and learning to harden current state-of-the-art reinforcement learning approaches before being mission-critical-ready.

Luca Cotti, Luca Lavazza, Marco Cominelli et al.

We address Human Activity Recognition (HAR) utilizing Wi-Fi Channel State Information (CSI) under the joint requirements of causal interpretability, symbolic controllability, and direct operation on high-dimensional raw signals. Deep neural models achieve strong predictive performance on CSI-based HAR (CHAR), yet rely on continuous latent representations that are opaque and difficult to modify; purely symbolic approaches, in contrast, cannot process raw CSI streams. We propose a fully automatic and strictly decoupled pipeline in which CSI magnitude windows are compressed by a categorical variational autoencoder with Gumbel-Softmax latent variables under a capacity-controlled objective, yielding a compact discrete representation. The encoder is then frozen and used as a deterministic mapping to one-hot latent trajectories. Causal discovery is performed on these trajectories to estimate class-conditional temporal dependency graphs. Statistically supported lagged dependencies are translated into Linear Temporal Logic (LTL) rules, producing a fully symbolic and deterministic classifier based solely on rule evaluation and aggregation, without any learned discriminative head. Because rules are defined over discrete latent variables, antenna-specific rule sets can in principle be combined at the symbolic level, enabling structured multi-antenna fusion without retraining the encoder. Results from CHAR Latent Temporal Rule Extraction (CHARL-TRE) indicate competitive performance while preserving explicit temporal and causal structure, showing that deterministic symbolic classification grounded in unsupervised discrete latent representations constitutes a viable alternative to end-to-end black-box models for wireless HAR.

Liying Han, Gaofeng Dong, Xiaomin Ouyang et al.

Complex events (CEs) play a crucial role in CPS-IoT applications, enabling high-level decision-making in domains such as smart monitoring and autonomous systems. However, most existing models focus on short-span perception tasks, lacking the long-term reasoning required for CE detection. CEs consist of sequences of short-time atomic events (AEs) governed by spatiotemporal dependencies. Detecting them is difficult due to long, noisy sensor data and the challenge of filtering out irrelevant AEs while capturing meaningful patterns. This work explores CE detection as a case study for CPS-IoT foundation models capable of long-term reasoning. We evaluate three approaches: (1) leveraging large language models (LLMs), (2) employing various neural architectures that learn CE rules from data, and (3) adopting a neurosymbolic approach that integrates neural models with symbolic engines embedding human knowledge. Our results show that the state-space model, Mamba, which belongs to the second category, outperforms all methods in accuracy and generalization to longer, unseen sensor traces. These findings suggest that state-space models could be a strong backbone for CPS-IoT foundation models for long-span reasoning tasks.

Murat Sensoy, Lance M. Kaplan, Simon Julier et al.

Autonomous and semi-autonomous systems are using deep learning models to improve decision-making. However, deep classifiers can be overly confident in their incorrect predictions, a major issue especially in safety-critical domains. The present study introduces three foundational desiderata for developing real-world risk-aware classification systems. Expanding upon the previously proposed Evidential Deep Learning (EDL), we demonstrate the unity between these principles and EDL's operational attributes. We then augment EDL empowering autonomous agents to exercise discretion during structured decision-making when uncertainty and risks are inherent. We rigorously examine empirical scenarios to substantiate these theoretical innovations. In contrast to existing risk-aware classifiers, our proposed methodologies consistently exhibit superior performance, underscoring their transformative potential in risk-conscious classification strategies.

Luca Cotti, Idilio Drago, Anisa Rula et al.

System logs represent a valuable source of Cyber Threat Intelligence (CTI), capturing attacker behaviors, exploited vulnerabilities, and traces of malicious activity. Yet their utility is often limited by lack of structure, semantic inconsistency, and fragmentation across devices and sessions. Extracting actionable CTI from logs therefore requires approaches that can reconcile noisy, heterogeneous data into coherent and interoperable representations. We introduce OntoLogX, an autonomous Artificial Intelligence (AI) agent that leverages Large Language Models (LLMs) to transform raw logs into ontology-grounded Knowledge Graphs (KGs). OntoLogX integrates a lightweight log ontology with Retrieval Augmented Generation (RAG) and iterative correction steps, ensuring that generated KGs are syntactically and semantically valid. Beyond event-level analysis, the system aggregates KGs into sessions and employs a LLM to predict MITRE ATT&CK tactics, linking low-level log evidence to higher-level adversarial objectives. We evaluate OntoLogX on both logs from a public benchmark and a real-world honeypot dataset, demonstrating robust KG generation across multiple KGs backends and accurate mapping of adversarial activity to ATT&CK tactics. Results highlight the benefits of retrieval and correction for precision and recall, the effectiveness of code-oriented models in structured log analysis, and the value of ontology-grounded representations for actionable CTI extraction.

Federico Cerutti

This paper presents a methodological approach to financial time series analysis by combining causal discovery and uncertainty-aware forecasting. As a case study, we focus on four key U.S. macroeconomic indicators -- GDP, economic growth, inflation, and unemployment -- and we apply the LPCMCI framework with Gaussian Process Distance Correlation (GPDC) to uncover dynamic causal relationships in quarterly data from 1970 to 2021. Our results reveal a robust unidirectional causal link from economic growth to GDP and highlight the limited connectivity of inflation, suggesting the influence of latent factors. Unemployment exhibits strong autoregressive dependence, motivating its use as a case study for probabilistic forecasting. Leveraging the Chronos framework, a large language model trained for time series, we perform zero-shot predictions on unemployment. This approach delivers accurate forecasts one and two quarters ahead, without requiring task-specific training. Crucially, the model's uncertainty-aware predictions yield 90\% confidence intervals, enabling effective anomaly detection through statistically principled deviation analysis. This study demonstrates the value of combining causal structure learning with probabilistic language models to inform economic policy and enhance forecasting robustness.

Luca Cotti, Anisa Rula, Devis Bianchini et al.

Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and interpret malicious events reliably and transparently, particularly in cases involving unstructured or ambiguous log entries. In this work, we propose a novel methodology that combines ontology-driven structured outputs with Large Language Models (LLMs), to build an Artificial Intelligence (AI) agent that improves the accuracy and explainability of information extraction from cybersecurity logs. Central to our approach is the integration of domain ontologies and SHACL-based constraints to guide the language model's output structure and enforce semantic validity over the resulting graph. Extracted information is organized into an ontology-enriched graph database, enabling future semantic analysis and querying. The design of our methodology is motivated by the analytical requirements associated with honeypot log data, which typically comprises predominantly malicious activity. While our case study illustrates the relevance of this scenario, the experimental evaluation is conducted using publicly available datasets. Results demonstrate that our method achieves higher accuracy in information extraction compared to traditional prompt-only approaches, with a deliberate focus on extraction quality rather than processing speed.

Alessandro Gaudenzi, Lorenzo Nodari, Lance Kaplan et al.

Advanced Persistent Threats (APTs) represent a significant challenge in cybersecurity due to their prolonged, multi-stage nature and the sophistication of their operators. Traditional detection systems typically focus on identifying malicious activity in binary terms (benign or malicious) without accounting for the progression of an attack. However, effective response strategies depend on accurate inference of the attack's current stage, as countermeasures must be tailored to whether an adversary is in the early reconnaissance phase or actively conducting exploitation or exfiltration. This work addresses the problem of attack stage inference under uncertainty, with a focus on robustness to out-of-distribution (OOD) inputs. We propose a classification approach based on Evidential Deep Learning (EDL), which models predictive uncertainty by outputting parameters of a Dirichlet distribution over possible stages. This allows the system not only to predict the most likely stage of an attack but also to indicate when it is uncertain or the input lies outside the training distribution. Preliminary experiments in a simulated environment demonstrate that the proposed model can accurately infer the stage of an attack with calibrated confidence while effectively detecting OOD inputs, which may indicate changes in the attackers' tactics. These results support the feasibility of deploying uncertainty-aware models for staged threat detection in dynamic and adversarial environments.

Kryspin Varys, Federico Cerutti, Adam Sobey et al.

Our society is governed by a set of norms which together bring about the values we cherish such as safety, fairness or trustworthiness. The goal of value-alignment is to create agents that not only do their tasks but through their behaviours also promote these values. Many of the norms are written as laws or rules (legal / safety norms) but even more remain unwritten (social norms). Furthermore, the techniques used to represent these norms also differ. Safety / legal norms are often represented explicitly, for example, in some logical language while social norms are typically learned and remain hidden in the parameter space of a neural network. There is a lack of approaches in the literature that could combine these various norm representations into a single algorithm. We propose a novel method that integrates these norms into the reinforcement learning process. Our method monitors the agent's compliance with the given norms and summarizes it in a quantity we call the agent's reputation. This quantity is used to weigh the received rewards to motivate the agent to become value-aligned. We carry out a series of experiments including a continuous state space traffic problem to demonstrate the importance of the written and unwritten norms and show how our method can find the value-aligned policies. Furthermore, we carry out ablations to demonstrate why it is better to combine these two groups of norms rather than using either separately.

Liying Han, Gaofeng Dong, Xiaomin Ouyang et al.

Modern machine learning models excel at detecting individual actions, objects, or scene attributes from short, local observations. However, many real-world tasks, such as in smart cities and healthcare, require reasoning over complex events (CEs): (spatio)temporal, rule-governed patterns of short-term atomic events (AEs) that reflect high-level understanding and critical changes in the environment. These CEs are difficult to detect online: they are often rare, require long-range reasoning over noisy sensor data, must generalize rules beyond fixed-length traces, and suffer from limited real-world datasets due to the high annotation burden. We propose NAROCE, a Neural Algorithmic Reasoning framework for Online CE detection that separates the task into two stages: (i) learning CE rules from large-scale, low-cost pseudo AE concept traces generated by simulators or LLMs, and (ii) training an adapter to map real sensor data into the learned reasoning space using fewer labeled sensor samples. Experiments show that NAROCE outperforms the strongest baseline in accuracy, generalization to longer, unseen sequences, and data efficiency, achieving comparable performance with less than half the labeled data. These results suggest that decoupling CE rule learning from raw sensor inputs improves both data efficiency and robustness.

Christian Bresciani, Federico Cerutti, Marco Cominelli

The thesis explores novel methods for Human Activity Recognition (HAR) using passive radar with a focus on non-intrusive Wi-Fi Channel State Information (CSI) data. Traditional HAR approaches often use invasive sensors like cameras or wearables, raising privacy issues. This study leverages the non-intrusive nature of CSI, using Spiking Neural Networks (SNN) to interpret signal variations caused by human movements. These networks, integrated with symbolic reasoning frameworks such as DeepProbLog, enhance the adaptability and interpretability of HAR systems. SNNs offer reduced power consumption, ideal for privacy-sensitive applications. Experimental results demonstrate SNN-based neurosymbolic models achieve high accuracy making them a promising alternative for HAR across various domains.

Olaf Lipinski, Adam J. Sobey, Federico Cerutti et al.

Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.

Marc Roig Vilamala, Tianwei Xing, Harrison Taylor et al.

In this paper, we present an approach to Complex Event Processing (CEP) that is based on DeepProbLog. This approach has the following objectives: (i) allowing the use of subsymbolic data as an input, (ii) retaining the flexibility and modularity on the definitions of complex event rules, (iii) allowing the system to be trained in an end-to-end manner and (iv) being robust against noisily labelled data. Our approach makes use of DeepProbLog to create a neuro-symbolic architecture that combines a neural network to process the subsymbolic data with a probabilistic logic layer to allow the user to define the rules for the complex events. We demonstrate that our approach is capable of detecting complex events from an audio stream. We also demonstrate that our approach is capable of training even with a dataset that has a moderate proportion of noisy data.

Matthias Thimm, Federico Cerutti, Mauro Vallati

We present Fudge, an abstract argumentation solver that tightly integrates satisfiability solving technology to solve a series of abstract argumentation problems. While most of the encodings used by Fudge derive from standard translation approaches, Fudge makes use of completely novel encodings to solve the skeptical reasoning problem wrt. preferred semantics and problems wrt. ideal semantics.

Federico Cerutti, Lance M. Kaplan, Angelika Kimmig et al.

When collaborating with an AI system, we need to assess when to trust its recommendations. If we mistakenly trust it in regions where it is likely to err, catastrophic failures may occur, hence the need for Bayesian approaches for probabilistic reasoning in order to determine the confidence (or epistemic uncertainty) in the probabilities in light of the training data. We propose an approach to overcome the independence assumption behind most of the approaches dealing with a large class of probabilistic reasoning that includes Bayesian networks as well as several instances of probabilistic logic. We provide an algorithm for Bayesian learning from sparse, albeit complete, observations, and for deriving inferences and their confidences keeping track of the dependencies between variables when they are manipulated within the unifying computational formalism provided by probabilistic circuits. Each leaf of such circuits is labelled with a beta-distributed random variable that provides us with an elegant framework for representing uncertain probabilities. We achieve better estimation of epistemic uncertainty than state-of-the-art approaches, including highly engineered ones, while being able to handle general circuits and with just a modest increase in the computational effort compared to using point probabilities.

Katie Barrett-Powell, Jack Furby, Liam Hiley et al.

We present an experimentation platform for coalition situational understanding research that highlights capabilities in explainable artificial intelligence/machine learning (AI/ML) and integration of symbolic and subsymbolic AI/ML approaches for event processing. The Situational Understanding Explorer (SUE) platform is designed to be lightweight, to easily facilitate experiments and demonstrations, and open. We discuss our requirements to support coalition multi-domain operations with emphasis on asset interoperability and ad hoc human-machine teaming in a dense urban terrain setting. We describe the interface functionality and give examples of SUE applied to coalition situational understanding tasks.

Dave Braines, Federico Cerutti, Marc Roig Vilamala et al.

Future coalition operations can be substantially augmented through agile teaming between human and machine agents, but in a coalition context these agents may be unfamiliar to the human users and expected to operate in a broad set of scenarios rather than being narrowly defined for particular purposes. In such a setting it is essential that the human agents can rapidly build trust in the machine agents through appropriate transparency of their behaviour, e.g., through explanations. The human agents are also able to bring their local knowledge to the team, observing the situation unfolding and deciding which key information should be communicated to the machine agents to enable them to better account for the particular environment. In this paper we describe the initial steps towards this human-agent knowledge fusion (HAKF) environment through a recap of the key requirements, and an explanation of how these can be fulfilled for an example situation. We show how HAKF has the potential to bring value to both human and machine agents working as part of a distributed coalition team in a complex event processing setting with uncertain sources.

Marc Roig Vilamala, Harrison Taylor, Tianwei Xing et al.

Training a model to detect patterns of interrelated events that form situations of interest can be a complex problem: such situations tend to be uncommon, and only sparse data is available. We propose a hybrid neuro-symbolic architecture based on Event Calculus that can perform Complex Event Processing (CEP). It leverages both a neural network to interpret inputs and logical rules that express the pattern of the complex event. Our approach is capable of training with much fewer labelled data than a pure neural network approach, and to learn to classify individual events even when training in an end-to-end manner. We demonstrate this comparing our approach against a pure neural network approach on a dataset based on Urban Sounds 8K.

Murat Sensoy, Lance Kaplan, Federico Cerutti et al.

Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. These approaches use an auxiliary data set during training to represent out-of-distribution samples. However, selection or creation of such an auxiliary data set is non-trivial, especially for high dimensional data such as images. In this work we develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions of the feature space. To this end, variational autoencoders and generative adversarial networks are incorporated to automatically generate out-of-distribution exemplars for training. Through extensive analysis, we demonstrate that the proposed approach provides better estimates of uncertainty for in- and out-of-distribution samples, and adversarial examples on well-known data sets against state-of-the-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.

Sam Vente, Angelika Kimmig, Alun Preece et al.

Automated negotiation can be an efficient method for resolving conflict and redistributing resources in a coalition setting. Automated negotiation has already seen increased usage in fields such as e-commerce and power distribution in smart girds, and recent advancements in opponent modelling have proven to deliver better outcomes. However, significant barriers to more widespread adoption remain, such as lack of predictable outcome over time and user trust. Additionally, there have been many recent advancements in the field of reasoning about uncertainty, which could help alleviate both those problems. As there is no recent survey on these two fields, and specifically not on their possible intersection we aim to provide such a survey here.

Sam Vente, Angelika Kimmig, Alun Preece et al.

Automated negotiation has been used in a variety of distributed settings, such as privacy in the Internet of Things (IoT) devices and power distribution in Smart Grids. The most common protocol under which these agents negotiate is the Alternating Offers Protocol (AOP). Under this protocol, agents cannot express any additional information to each other besides a counter offer. This can lead to unnecessarily long negotiations when, for example, negotiations are impossible, risking to waste bandwidth that is a precious resource at the edge of the network. While alternative protocols exist which alleviate this problem, these solutions are too complex for low power devices, such as IoT sensors operating at the edge of the network. To improve this bottleneck, we introduce an extension to AOP called Alternating Constrained Offers Protocol (ACOP), in which agents can also express constraints to each other. This allows agents to both search the possibility space more efficiently and recognise impossible situations sooner. We empirically show that agents using ACOP can significantly reduce the number of messages a negotiation takes, independently of the strategy agents choose. In particular, we show our method significantly reduces the number of messages when an agreement is not possible. Furthermore, when an agreement is possible it reaches this agreement sooner with no negative effect on the utility.

Alun Preece, Dave Braines, Federico Cerutti et al.

Central to the concept of multi-domain operations (MDO) is the utilization of an intelligence, surveillance, and reconnaissance (ISR) network consisting of overlapping systems of remote and autonomous sensors, and human intelligence, distributed among multiple partners. Realising this concept requires advancement in both artificial intelligence (AI) for improved distributed data analytics and intelligence augmentation (IA) for improved human-machine cognition. The contribution of this paper is threefold: (1) we map the coalition situational understanding (CSU) concept to MDO ISR requirements, paying particular attention to the need for assured and explainable AI to allow robust human-machine decision-making where assets are distributed among multiple partners; (2) we present illustrative vignettes for AI and IA in MDO ISR, including human-machine teaming, dense urban terrain analysis, and enhanced asset interoperability; (3) we appraise the state-of-the-art in explainable AI in relation to the vignettes with a focus on human-machine collaboration to achieve more rapid and agile coalition decision-making. The union of these three elements is intended to show the potential value of a CSU approach in the context of MDO ISR, grounded in three distinct use cases, highlighting how the need for explainability in the multi-partner coalition setting is key.

Pietro Baroni, Federico Cerutti, Paul E. Dunne et al.

The theory of abstract argumentation frameworks (afs) has, in the main, focused on finite structures, though there are many significant contexts where argumentation can be regarded as a process involving infinite objects. To address this limitation, in this paper we propose a novel approach for describing infinite afs using tools from formal language theory. In particular, the possibly infinite set of arguments is specified through the language recognized by a deterministic finite automaton while a suitable formalism, called attack expression, is introduced to describe the relation of attack between arguments. The proposed approach is shown to satisfy some desirable properties which can not be achieved through other "naive" uses of formal languages. In particular, the approach is shown to be expressive enough to capture (besides any arbitrary finite structure) a large variety of infinite afs including two major examples from previous literature and two sample cases from the domains of multi-agent negotiation and ambient intelligence. On the computational side, we show that several decision and construction problems which are known to be polynomial time solvable in finite afs are decidable in the context of the proposed formalism and we provide the relevant algorithms. Moreover we obtain additional results concerning the case of finitary afs.

Pietro Baroni, Federico Cerutti, Massimiliano Giacomin et al.

The issue of representing attacks to attacks in argumentation is receiving an increasing attention as a useful conceptual modelling tool in several contexts. In this paper we present AFRA, a formalism encompassing unlimited recursive attacks within argumentation frameworks. AFRA satisfies the basic requirements of definition simplicity and rigorous compatibility with Dung's theory of argumentation. This paper provides a complete development of the AFRA formalism complemented by illustrative examples and a detailed comparison with other recursive attack formalizations.

Federico Cerutti, Lance Kaplan, Angelika Kimmig et al.

We enable aProbLog---a probabilistic logical programming approach---to reason in presence of uncertain probabilities represented as Beta-distributed random variables. We achieve the same performance of state-of-the-art algorithms for highly specified and engineered domains, while simultaneously we maintain the flexibility offered by aProbLog in handling complex relational domains. Our motivation is that faithfully capturing the distribution of probabilities is necessary to compute an expected utility for effective decision making under uncertainty: unfortunately, these probability distributions can be highly uncertain due to sparse data. To understand and accurately manipulate such probability distributions we need a well-defined theoretical framework that is provided by the Beta distribution, which specifies a distribution of probabilities representing all the possible values of a probability when the exact value is unknown.

Lance Kaplan, Federico Cerutti, Murat Sensoy et al.

This paper argues the need for research to realize uncertainty-aware artificial intelligence and machine learning (AI\&ML) systems for decision support by describing a number of motivating scenarios. Furthermore, the paper defines uncertainty-awareness and lays out the challenges along with surveying some promising research directions. A theoretical demonstration illustrates how two emerging uncertainty-aware ML and AI technologies could be integrated and be of value for a route planning operation.

Federico Cerutti, Alice Toniolo, Timothy J. Norman

In this paper we provide a first analysis of the research questions that arise when dealing with the problem of communicating pieces of formal argumentation through natural language interfaces. It is a generally held opinion that formal models of argumentation naturally capture human argument, and some preliminary studies have focused on justifying this view. Unfortunately, the results are not only inconclusive, but seem to suggest that explaining formal argumentation to humans is a rather articulated task. Graphical models for expressing argumentation-based reasoning are appealing, but often humans require significant training to use these tools effectively. We claim that natural language interfaces to formal argumentation systems offer a real alternative, and may be the way forward for systems that capture human argument.

Wolfgang Faber, Mauro Vallati, Federico Cerutti et al.

Optimization - minimization or maximization - in the lattice of subsets is a frequent operation in Artificial Intelligence tasks. Examples are subset-minimal model-based diagnosis, nonmonotonic reasoning by means of circumscription, or preferred extensions in abstract argumentation. Finding the optimum among many admissible solutions is often harder than finding admissible solutions with respect to both computational complexity and methodology. This paper addresses the former issue by means of an effective method for finding subset-optimal solutions. It is based on the relationship between cardinality-optimal and subset-optimal solutions, and the fact that many logic-based declarative programming systems provide constructs for finding cardinality-optimal solutions, for example maximum satisfiability (MaxSAT) or weak constraints in Answer Set Programming (ASP). Clearly each cardinality-optimal solution is also a subset-optimal one, and if the language also allows for the addition of particular restricting constructs (both MaxSAT and ASP do) then all subset-optimal solutions can be found by an iterative computation of cardinality-optimal solutions. As a showcase, the computation of preferred extensions of abstract argumentation frameworks using the proposed method is studied.

Federico Cerutti, Ilias Tachmazidis, Mauro Vallati et al.

Abstract argumentation framework (\AFname) is a unifying framework able to encompass a variety of nonmonotonic reasoning approaches, logic programming and computational argumentation. Yet, efficient approaches for most of the decision and enumeration problems associated to \AFname s are missing, thus potentially limiting the efficacy of argumentation-based approaches in real domains. In this paper, we present an algorithm for enumerating the preferred extensions of abstract argumentation frameworks which exploits parallel computation. To this purpose, the SCC-recursive semantics definition schema is adopted, where extensions are defined at the level of specific sub-frameworks. The algorithm shows significant performance improvements in large frameworks, in terms of number of solutions found and speedup.

Chatschik Bisdikian, Federico Cerutti, Yuqing Tang et al.

In this paper we describe a decision process framework allowing an agent to decide what information it should reveal to its neighbours within a communication graph in order to maximise its utility. We assume that these neighbours can pass information onto others within the graph. The inferences made by agents receiving the messages can have a positive or negative impact on the information providing agent, and our decision process seeks to identify how a message should be modified in order to be most beneficial to the information producer. Our decision process is based on the provider's subjective beliefs about others in the system, and therefore makes extensive use of the notion of trust. Our core contributions are therefore the construction of a model of information propagation; the description of the agent's decision procedure; and an analysis of some of its properties.

Federico Cerutti, Alice Toniolo, Nir Oren et al.

Computational trust mechanisms aim to produce trust ratings from both direct and indirect information about agents' behaviour. Subjective Logic (SL) has been widely adopted as the core of such systems via its fusion and discount operators. In recent research we revisited the semantics of these operators to explore an alternative, geometric interpretation. In this paper we present a principled desiderata for discounting and fusion operators in SL. Building upon this we present operators that satisfy these desirable properties, including a family of discount operators. We then show, through a rigorous empirical study, that specific, geometrically interpreted operators significantly outperform standard SL operators in estimating ground truth. These novel operators offer real advantages for computational models of trust and reputation, in which they may be employed without modifying other aspects of an existing system.

Federico Cerutti, Paul E. Dunne, Massimiliano Giacomin et al.

This paper presents a novel SAT-based approach for the computation of extensions in abstract argumentation, with focus on preferred semantics, and an empirical evaluation of its performances. The approach is based on the idea of reducing the problem of computing complete extensions to a SAT problem and then using a depth-first search method to derive preferred extensions. The proposed approach has been tested using two distinct SAT solvers and compared with three state-of-the-art systems for preferred extension computation. It turns out that the proposed approach delivers significantly better performances in the large majority of the considered cases.