Research Papers

A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence

Justus Renkhoff, Ke Feng, Marc Meier-Doernberg +2

Neurosymbolic artificial intelligence (AI) is an emerging branch of AI that combines the strengths of symbolic AI and sub-symbolic AI. A major drawback of sub-symbolic AI is that it acts as a "black box", meaning that predictions are difficult to explain, making the testing & evaluation (T&E) and validation & verification (V&V) processes of a system that uses sub-symbolic AI a challenge. Since neurosymbolic AI combines the advantages of both symbolic and sub-symbolic AI, this survey explores how neurosymbolic applications can ease the V&V process. This survey considers two taxonomies of neurosymbolic AI, evaluates them, and analyzes which algorithms are commonly used as the symbolic and sub-symbolic components in current applications. Additionally, an overview of current techniques for the T&E and V&V processes of these components is provided. Furthermore, it is investigated how the symbolic part is used for T&E and V&V purposes in current neurosymbolic applications. Our research shows that neurosymbolic AI as great potential to ease the T&E and V&V processes of sub-symbolic AI by leveraging the possibilities of symbolic AI. Additionally, the applicability of current T&E and V&V methods to neurosymbolic AI is assessed, and how different neurosymbolic architectures can impact these methods is explored. It is found that current T&E and V&V techniques are partly sufficient to test, evaluate, verify, or validate the symbolic and sub-symbolic part of neurosymbolic applications independently, while some of them use approaches where current T&E and V&V methods are not applicable by default, and adjustments or even new approaches are needed. Our research shows that there is great potential in using symbolic AI to test, evaluate, verify, or validate the predictions of a sub-symbolic model, making neurosymbolic AI an interesting research direction for safe, secure, and trustworthy AI.

AI in Supply Chain Risk Assessment: A Systematic Literature Review and Bibliometric Analysis

Md Abrar Jahin, Saleh Akram Naife, Anik Kumar Saha +1

Supply chain risk assessment (SCRA) is pivotal for ensuring resilience in increasingly complex global supply networks. While existing reviews have explored traditional methodologies, they often neglect emerging artificial intelligence (AI) and machine learning (ML) applications and mostly lack combined systematic and bibliometric analyses. This study addresses these gaps by integrating a systematic literature review with bibliometric analysis, examining 1,903 articles (2015-2025), with 54 studies selected through PRISMA guidelines. Our findings reveal that ML models, including Random Forest, XGBoost, and hybrid approaches, significantly improve risk prediction accuracy and adaptability in post-pandemic contexts. The bibliometric analysis identifies key trends, influential authors, and institutional contributions, highlighting China and the United States as leading research hubs. Practical insights emphasize the integration of explainable AI (XAI) for transparent decision-making, real-time data utilization, and blockchain for traceability. The study underscores the necessity of dynamic strategies, interdisciplinary collaboration, and continuous model evaluation to address challenges such as data quality and interpretability. By synthesizing AI-driven methodologies with resilience frameworks, this review provides actionable guidance for optimizing supply chain risk management, fostering adaptability, and informing future research in evolving risk landscapes.

Cyber Sentinel: Exploring Conversational Agents in Streamlining Security Tasks with GPT-4

Mehrdad Kaheh, Danial Khosh Kholgh, Panos Kostakos

In an era where cyberspace is both a battleground and a backbone of modern society, the urgency of safeguarding digital assets against ever-evolving threats is paramount. This paper introduces Cyber Sentinel, an innovative task-oriented cybersecurity dialogue system that is effectively capable of managing two core functions: explaining potential cyber threats within an organization to the user, and taking proactive/reactive security actions when instructed by the user. Cyber Sentinel embodies the fusion of artificial intelligence, cybersecurity domain expertise, and real-time data analysis to combat the multifaceted challenges posed by cyber adversaries. This article delves into the process of creating such a system and how it can interact with other components typically found in cybersecurity organizations. Our work is a novel approach to task-oriented dialogue systems, leveraging the power of chaining GPT-4 models combined with prompt engineering across all sub-tasks. We also highlight its pivotal role in enhancing cybersecurity communication and interaction, concluding that not only does this framework enhance the system's transparency (Explainable AI) but also streamlines the decision-making process and responding to threats (Actionable AI), therefore marking a significant advancement in the realm of cybersecurity communication.

Contemporary DNN testing works are frequently conducted using metamorphic testing (MT). In general, de facto MT frameworks mutate DNN input images using semantics-preserving mutations and determine if DNNs can yield consistent predictions. Nevertheless, we find that DNNs may rely on erroneous decisions (certain components on the DNN inputs) to make predictions, which may still retain the outputs by chance. Such DNN defects would be neglected by existing MT frameworks. Erroneous decisions, however, would likely result in successive mis-predictions over diverse images that may exist in real-life scenarios. This research aims to unveil the pervasiveness of hidden DNN defects caused by incorrect DNN decisions (but retaining consistent DNN predictions). To do so, we tailor and optimize modern eXplainable AI (XAI) techniques to identify visual concepts that represent regions in an input image upon which the DNN makes predictions. Then, we extend existing MT-based DNN testing frameworks to check the consistency of DNN decisions made over a test input and its mutated inputs. Our evaluation shows that existing MT frameworks are oblivious to a considerable number of DNN defects caused by erroneous decisions. We conduct human evaluations to justify the validity of our findings and to elucidate their characteristics. Through the lens of DNN decision-based metamorphic relations, we re-examine the effectiveness of metamorphic transformations proposed by existing MT frameworks. We summarize lessons from this study, which can provide insights and guidelines for future DNN testing.

Diagnosing AI Explanation Methods with Folk Concepts of Behavior

Alon Jacovi, Jasmijn Bastings, Sebastian Gehrmann +2

We investigate a formalism for the conditions of a successful explanation of AI. We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. Theory of mind literature discusses the folk concepts that humans use to understand and generalize behavior. We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with. We use these folk concepts as a framework of social attribution by the human explainee - the information constructs that humans are likely to comprehend from explanations - by introducing a blueprint for an explanatory narrative (Figure 1) that explains AI behavior with these constructs. We then demonstrate that many XAI methods today can be mapped to folk concepts of behavior in a qualitative evaluation. This allows us to uncover their failure modes that prevent current methods from explaining successfully - i.e., the information constructs that are missing for any given XAI method, and whose inclusion can decrease the likelihood of misunderstanding AI behavior.

Explainability is becoming an important requirement for organizations that make use of automated decision-making due to regulatory initiatives and a shift in public awareness. Various and significantly different algorithmic methods to provide this explainability have been introduced in the field, but the existing literature in the machine learning community has paid little attention to the stakeholder whose needs are rather studied in the human-computer interface community. Therefore, organizations that want or need to provide this explainability are confronted with the selection of an appropriate method for their use case. In this paper, we argue there is a need for a methodology to bridge the gap between stakeholder needs and explanation methods. We present our ongoing work on creating this methodology to help data scientists in the process of providing explainability to stakeholders. In particular, our contributions include documents used to characterize XAI methods and user requirements (shown in Appendix), which our methodology builds upon.

Recent years have witnessed a renewed interest in Boolean function in explaining binary classifiers in the field of explainable AI (XAI). The standard approach of Boolean function is propositional logic. We present a modal language of a ceteris paribus nature which supports reasoning about binary input classifiers and their properties. We study a family of classifier models, axiomatize it as two proof systems regarding the cardinality of the language and show completeness of our axiomatics. Moreover, we prove that satisfiability checking problem for our modal language is NEXPTIME-complete in the infinite-variable case, while it becomes polynomial in the finite-variable case. We furthermore identify an interesting NP fragment of our language in the infinite-variable case. We leverage the language to formalize counterfactual conditional as well as a variety of notions of explanation including abductive, contrastive and counterfactual explanations, and biases. Finally, we present two extensions of our language: a dynamic extension by the notion of assignment enabling classifier change and an epistemic extension in which the classifier's uncertainty about the actual input can be represented.

Explainable AI(XAI)is a domain focused on providing interpretability and explainability of a decision-making process. In the domain of law, in addition to system and data transparency, it also requires the (legal-) decision-model transparency and the ability to understand the models inner working when arriving at the decision. This paper provides the first approaches to using a popular image processing technique, Grad-CAM, to showcase the explainability concept for legal texts. With the help of adapted Grad-CAM metrics, we show the interplay between the choice of embeddings, its consideration of contextual information, and their effect on downstream processing.

Recent developments in Artificial Intelligence (AI) and their applications in critical industries such as healthcare, fin-tech and cybersecurity have led to a surge in research in explainability in AI. Innovative research methods are being explored to extract meaningful insight from blackbox AI systems to make the decision-making technology transparent and interpretable. Explainability becomes all the more critical when AI is used in decision making in domains like fintech, healthcare and safety critical systems such as cybersecurity and autonomous vehicles. However, there is still ambiguity lingering on the reliable evaluations for the users and nature of transparency in the explanations provided for the decisions made by black-boxed AI. To solve the blackbox nature of Machine Learning based Intrusion Detection Systems, a framework is proposed in this paper to give an explanation for IDSs decision making. This framework uses Local Interpretable Model-Agnostic Explanations (LIME) coupled with Explain Like I'm five (ELI5) and Decision Tree algorithms to provide local and global explanations and improve the interpretation of IDSs. The local explanations provide the justification for the decision made on a specific input. Whereas, the global explanations provides the list of significant features and their relationship with attack traffic. In addition, this framework brings transparency in the field of ML driven IDS that might be highly significant for wide scale adoption of eXplainable AI in cyber-critical systems. Our framework is able to achieve 85 percent accuracy in classifying attack behaviour on UNSW-NB15 dataset, while at the same time displaying the feature significance ranking of the top 10 features used in the classification.

Explainable Artificial Intelligence (AI) methods are designed to provide information about how AI-based models make predictions. In healthcare, there is a widespread expectation that these methods will provide relevant and accurate information about a model's inner-workings to different stakeholders (ranging from patients and healthcare providers to AI and medical guideline developers). This is a challenging endeavour since what qualifies as relevant information may differ greatly depending on the stakeholder. For many stakeholders, relevant explanations are causal in nature, yet, explainable AI methods are often not able to deliver this information. Using the Describe-Predict-Explain framework, we argue that Explainable AI methods are good descriptive tools, as they may help to describe how a model works but are limited in their ability to explain why a model works in terms of true underlying biological mechanisms and cause-and-effect relations. This limits the suitability of explainable AI methods to provide actionable advice to patients or to judge the face validity of AI-based models.

Digital twin models are of high interest to Head and Neck Cancer (HNC) oncologists, who have to navigate a series of complex treatment decisions that weigh the efficacy of tumor control against toxicity and mortality risks. Evaluating individual risk profiles necessitates a deeper understanding of the interplay between different factors such as patient health, spatial tumor location and spread, and risk of subsequent toxicities that can not be adequately captured through simple heuristics. To support clinicians in better understanding tradeoffs when deciding on treatment courses, we developed DITTO, a digital-twin and visual computing system that allows clinicians to analyze detailed risk profiles for each patient, and decide on a treatment plan. DITTO relies on a sequential Deep Reinforcement Learning digital twin (DT) to deliver personalized risk of both long-term and short-term disease outcome and toxicity risk for HNC patients. Based on a participatory collaborative design alongside oncologists, we also implement several visual explainability methods to promote clinical trust and encourage healthy skepticism when using our system. We evaluate the efficacy of DITTO through quantitative evaluation of performance and case studies with qualitative feedback. Finally, we discuss design lessons for developing clinical visual XAI applications for clinical end users.

Multiple instance learning (MIL) is an effective and widely used approach for weakly supervised machine learning. In histopathology, MIL models have achieved remarkable success in tasks like tumor detection, biomarker prediction, and outcome prognostication. However, MIL explanation methods are still lagging behind, as they are limited to small bag sizes or disregard instance interactions. We revisit MIL through the lens of explainable AI (XAI) and introduce xMIL, a refined framework with more general assumptions. We demonstrate how to obtain improved MIL explanations using layer-wise relevance propagation (LRP) and conduct extensive evaluation experiments on three toy settings and four real-world histopathology datasets. Our approach consistently outperforms previous explanation attempts with particularly improved faithfulness scores on challenging biomarker prediction tasks. Finally, we showcase how xMIL explanations enable pathologists to extract insights from MIL models, representing a significant advance for knowledge discovery and model debugging in digital histopathology. Codes are available at: https://github.com/bifold-pathomics/xMIL.