Research Papers

Creativity is a fundamental skill of human cognition. We use textual forma mentis networks (TFMN) to extract network (semantic/syntactic associations) and emotional features from approximately one thousand human- and GPT3.5-generated stories. Using Explainable Artificial Intelligence (XAI), we test whether features relative to Mednick's associative theory of creativity can explain creativity ratings assigned by humans and GPT-3.5. Using XGBoost, we examine three scenarios: (i) human ratings of human stories, (ii) GPT-3.5 ratings of human stories, and (iii) GPT-3.5 ratings of GPT-generated stories. Our findings reveal that GPT-3.5 ratings differ significantly from human ratings not only in terms of correlations but also because of feature patterns identified with XAI methods. GPT-3.5 favours 'its own' stories and rates human stories differently from humans. Feature importance analysis with SHAP scores shows that: (i) network features are more predictive for human creativity ratings but also for GPT-3.5's ratings of human stories; (ii) emotional features played a greater role than semantic/syntactic network structure in GPT-3.5 rating its own stories. These quantitative results underscore key limitations in GPT-3.5's ability to align with human assessments of creativity. We emphasise the need for caution when using GPT-3.5 to assess and generate creative content, as it does not yet capture the nuanced complexity that characterises human creativity.

Leveraging Gene Expression Data and Explainable Machine Learning for Enhanced Early Detection of Type 2 Diabetes

Aurora Lithe Roy, Md Kamrul Siam, Nuzhat Noor Islam Prova +2

Diabetes, particularly Type 2 diabetes (T2D), poses a substantial global health burden, compounded by its associated complications such as cardiovascular diseases, kidney failure, and vision impairment. Early detection of T2D is critical for improving healthcare outcomes and optimizing resource allocation. In this study, we address the gap in early T2D detection by leveraging machine learning (ML) techniques on gene expression data obtained from T2D patients. Our primary objective was to enhance the accuracy of early T2D detection through advanced ML methodologies and increase the model's trustworthiness using the explainable artificial intelligence (XAI) technique. Analyzing the biological mechanisms underlying T2D through gene expression datasets represents a novel research frontier, relatively less explored in previous studies. While numerous investigations have focused on utilizing clinical and demographic data for T2D prediction, the integration of molecular insights from gene expression datasets offers a unique and promising avenue for understanding the pathophysiology of the disease. By employing six ML classifiers on data sourced from NCBI's Gene Expression Omnibus (GEO), we observed promising performance across all models. Notably, the XGBoost classifier exhibited the highest accuracy, achieving 97%. Our study addresses a notable gap in early T2D detection methodologies, emphasizing the importance of leveraging gene expression data and advanced ML techniques.

South Africa and the Democratic Republic of Congo (DRC) present a complex linguistic landscape with languages such as Zulu, Sepedi, Afrikaans, French, English, and Tshiluba (Ciluba), which creates unique challenges for AI-driven translation and sentiment analysis systems due to a lack of accurately labeled data. This study seeks to address these challenges by developing a multilingual lexicon designed for French and Tshiluba, now expanded to include translations in English, Afrikaans, Sepedi, and Zulu. The lexicon enhances cultural relevance in sentiment classification by integrating language-specific sentiment scores. A comprehensive testing corpus is created to support translation and sentiment analysis tasks, with machine learning models such as Random Forest, Support Vector Machine (SVM), Decision Trees, and Gaussian Naive Bayes (GNB) trained to predict sentiment across low resource languages (LRLs). Among them, the Random Forest model performed particularly well, capturing sentiment polarity and handling language-specific nuances effectively. Furthermore, Bidirectional Encoder Representations from Transformers (BERT), a Large Language Model (LLM), is applied to predict context-based sentiment with high accuracy, achieving 99% accuracy and 98% precision, outperforming other models. The BERT predictions were clarified using Explainable AI (XAI), improving transparency and fostering confidence in sentiment classification. Overall, findings demonstrate that the proposed lexicon and machine learning models significantly enhance translation and sentiment analysis for LRLs in South Africa and the DRC, laying a foundation for future AI models that support underrepresented languages, with applications across education, governance, and business in multilingual contexts.

Explainable Artificial Intelligence (XAI) emerged to reveal the internal mechanism of machine learning models and how the features affect the prediction outcome. Collinearity is one of the big issues that XAI methods face when identifying the most informative features in the model. Current XAI approaches assume the features in the models are independent and calculate the effect of each feature toward model prediction independently from the rest of the features. However, such assumption is not realistic in real life applications. We propose an Additive Effects of Collinearity (AEC) as a novel XAI method that aim to considers the collinearity issue when it models the effect of each feature in the model on the outcome. AEC is based on the idea of dividing multivariate models into several univariate models in order to examine their impact on each other and consequently on the outcome. The proposed method is implemented using simulated and real data to validate its efficiency comparing with the a state of arts XAI method. The results indicate that AEC is more robust and stable against the impact of collinearity when it explains AI models compared with the state of arts XAI method.

A Methodology for Incompleteness-Tolerant and Modular Gradual Semantics for Argumentative Statement Graphs

Antonio Rago, Stylianos Loukas Vasileiou, Francesca Toni +2

Gradual semantics (GS) have demonstrated great potential in argumentation, in particular for deploying quantitative bipolar argumentation frameworks (QBAFs) in a number of real-world settings, from judgmental forecasting to explainable AI. In this paper, we provide a novel methodology for obtaining GS for statement graphs, a form of structured argumentation framework, where arguments and relations between them are built from logical statements. Our methodology differs from existing approaches in the literature in two main ways. First, it naturally accommodates incomplete information, so that arguments with partially specified premises can play a meaningful role in the evaluation. Second, it is modularly defined to leverage on any GS for QBAFs. We also define a set of novel properties for our GS and study their suitability alongside a set of existing properties (adapted to our setting) for two instantiations of our GS, demonstrating their advantages over existing approaches.

Countering Autonomous Cyber Threats

Kade M. Heckel, Adrian Weller

With the capability to write convincing and fluent natural language and generate code, Foundation Models present dual-use concerns broadly and within the cyber domain specifically. Generative AI has already begun to impact cyberspace through a broad illicit marketplace for assisting malware development and social engineering attacks through hundreds of malicious-AI-as-a-services tools. More alarming is that recent research has shown the potential for these advanced models to inform or independently execute offensive cyberspace operations. However, these previous investigations primarily focused on the threats posed by proprietary models due to the until recent lack of strong open-weight model and additionally leave the impacts of network defenses or potential countermeasures unexplored. Critically, understanding the aptitude of downloadable models to function as offensive cyber agents is vital given that they are far more difficult to govern and prevent their misuse. As such, this work evaluates several state-of-the-art FMs on their ability to compromise machines in an isolated network and investigates defensive mechanisms to defeat such AI-powered attacks. Using target machines from a commercial provider, the most recently released downloadable models are found to be on par with a leading proprietary model at conducting simple cyber attacks with common hacking tools against known vulnerabilities. To mitigate such LLM-powered threats, defensive prompt injection (DPI) payloads for disrupting the malicious cyber agent's workflow are demonstrated to be effective. From these results, the implications for AI safety and governance with respect to cybersecurity is analyzed.

eXplainable Artificial Intelligence (XAI) has garnered significant attention for enhancing transparency and trust in machine learning models. However, the scopes of most existing explanation techniques focus either on offering a holistic view of the explainee model (global explanation) or on individual instances (local explanation), while the middle ground, i.e., cohort-based explanation, is less explored. Cohort explanations offer insights into the explainee's behavior on a specific group or cohort of instances, enabling a deeper understanding of model decisions within a defined context. In this paper, we discuss the unique challenges and opportunities associated with measuring cohort explanations, define their desired properties, and create a generalized framework for generating cohort explanations based on supervised clustering.

As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks often overlooked in traditional AI risk assessment frameworks. This paper introduces a novel formal framework for categorizing and mitigating these emergent security risks by integrating adaptive, real-time monitoring, and dynamic risk mitigation strategies tailored to generative models' unique vulnerabilities. We identify previously under-explored risks, including latent space exploitation, multi-modal cross-attack vectors, and feedback-loop-induced model degradation. Our framework employs a layered approach, incorporating anomaly detection, continuous red-teaming, and real-time adversarial simulation to mitigate these risks. We focus on formal verification methods to ensure model robustness and scalability in the face of evolving threats. Though theoretical, this work sets the stage for future empirical validation by establishing a detailed methodology and metrics for evaluating the performance of risk mitigation strategies in generative AI systems. This framework addresses existing gaps in AI safety, offering a comprehensive road map for future research and implementation.

In November 2023, the UK and US announced the creation of their AI Safety Institutes (AISIs). Five other jurisdictions have followed in establishing AISIs or similar institutions, with more likely to follow. While there is considerable variation between these institutions, there are also key similarities worth identifying. This primer describes one cluster of similar AISIs, the "first wave," consisting of the Japan, UK, and US AISIs. First-wave AISIs have several fundamental characteristics in common: they are technical government institutions, have a clear mandate related to the safety of advanced AI systems, and lack regulatory powers. Safety evaluations are at the center of first-wave AISIs. These techniques test AI systems across tasks to understand their behavior and capabilities on relevant risks, such as cyber, chemical, and biological misuse. They also share three core functions: research, standards, and cooperation. These functions are critical to AISIs' work on safety evaluations but also support other activities such as scientific consensus-building and foundational AI safety research. Despite its growing popularity as an institutional model, the AISI model is not free from challenges and limitations. Some analysts have criticized the first wave of AISIs for specializing too much in a sub-area and for being potentially redundant with existing institutions, for example. Future developments may rapidly change this landscape, and particularities of individual AISIs may not be captured by our broad-strokes description. This policy brief aims to outline the core elements of first-wave AISIs as a way of encouraging and improving conversations on this novel institutional model, acknowledging this is just a simplified snapshot rather than a timeless prescription.

Natural Language Counterfactual Explanations for Graphs Using Large Language Models

Flavio Giorgi, Cesare Campagnano, Fabrizio Silvestri +1

Explainable Artificial Intelligence (XAI) has emerged as a critical area of research to unravel the opaque inner logic of (deep) machine learning models. Among the various XAI techniques proposed in the literature, counterfactual explanations stand out as one of the most promising approaches. However, these "what-if" explanations are frequently complex and technical, making them difficult for non-experts to understand and, more broadly, challenging for humans to interpret. To bridge this gap, in this work, we exploit the power of open-source Large Language Models to generate natural language explanations when prompted with valid counterfactual instances produced by state-of-the-art explainers for graph-based models. Experiments across several graph datasets and counterfactual explainers show that our approach effectively produces accurate natural language representations of counterfactual instances, as demonstrated by key performance metrics.

Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an evolving combination of adversarial training and guardrails. However, managing the implicit and heterogeneous knowledge for continuously assuring robustness is difficult. We introduce a novel approach for assurance of the adversarial robustness of LLMs based on formal argumentation. Using ontologies for formalization, we structure state-of-the-art attacks and defenses, facilitating the creation of a human-readable assurance case, and a machine-readable representation. We demonstrate its application with examples in English language and code translation tasks, and provide implications for theory and practice, by targeting engineers, data scientists, users, and auditors.

Learning from Demonstration (LfD) is a powerful type of machine learning that can allow novices to teach and program robots to complete various tasks. However, the learning process for these systems may still be difficult for novices to interpret and understand, making effective teaching challenging. Explainable artificial intelligence (XAI) aims to address this challenge by explaining a system to the user. In this work, we investigate XAI within LfD by implementing an adaptive explanatory feedback system on an inverse reinforcement learning (IRL) algorithm. The feedback is implemented by demonstrating selected learnt trajectories to users. The system adapts to user teaching by categorizing and then selectively sampling trajectories shown to a user, to show a representative sample of both successful and unsuccessful trajectories. The system was evaluated through a user study with 26 participants teaching a robot a navigation task. The results of the user study demonstrated that the proposed explanatory feedback system can improve robot performance, teaching efficiency and user understanding of the robot.