Research Papers

LLMs demand significant computational resources for both pre-training and fine-tuning, requiring distributed computing capabilities due to their large model sizes \cite{sastry2024computing}. Their complex architecture poses challenges throughout the entire AI lifecycle, from data collection to deployment and monitoring \cite{OECD_AIlifecycle}. Addressing critical AI system challenges, such as explainability, corrigibility, interpretability, and hallucination, necessitates a systematic methodology and rigorous benchmarking \cite{guldimann2024complai}. To effectively improve AI systems, we must precisely identify systemic vulnerabilities through quantitative evaluation, bolstering system trustworthiness. The enactment of the EU AI Act \cite{EUAIAct} by the European Parliament on March 13, 2024, establishing the first comprehensive EU-wide requirements for the development, deployment, and use of AI systems, further underscores the importance of tools and methodologies such as Z-Inspection. It highlights the need to enrich this methodology with practical benchmarks to effectively address the technical challenges posed by AI systems. To this end, we have launched a project that is part of the AI Safety Bulgaria initiatives \cite{AI_Safety_Bulgaria}, aimed at collecting and categorizing AI benchmarks. This will enable practitioners to identify and utilize these benchmarks throughout the AI system lifecycle.

This article presents the design of an open-API-based explainable AI (XAI) service to provide feature contribution explanations for cloud AI services. Cloud AI services are widely used to develop domain-specific applications with precise learning metrics. However, the underlying cloud AI services remain opaque on how the model produces the prediction. We argue that XAI operations are accessible as open APIs to enable the consolidation of the XAI operations into the cloud AI services assessment. We propose a design using a microservice architecture that offers feature contribution explanations for cloud AI services without unfolding the network structure of the cloud models. We can also utilize this architecture to evaluate the model performance and XAI consistency metrics showing cloud AI services trustworthiness. We collect provenance data from operational pipelines to enable reproducibility within the XAI service. Furthermore, we present the discovery scenarios for the experimental tests regarding model performance and XAI consistency metrics for the leading cloud vision AI services. The results confirm that the architecture, based on open APIs, is cloud-agnostic. Additionally, data augmentations result in measurable improvements in XAI consistency metrics for cloud AI services.

Graph Neural Networks (GNNs) are a powerful technique for machine learning on graph-structured data, yet they pose challenges in interpretability. Existing GNN explanation methods usually yield technical outputs, such as subgraphs and feature importance scores, that are difficult for non-data scientists to understand and thereby violate the purpose of explanations. Motivated by recent Explainable AI (XAI) research, we propose GraphXAIN, a method that generates natural language narratives explaining GNN predictions. GraphXAIN is a model- and explainer-agnostic method that uses Large Language Models (LLMs) to translate explanatory subgraphs and feature importance scores into coherent, story-like explanations of GNN decision-making processes. Evaluations on real-world datasets demonstrate GraphXAIN's ability to improve graph explanations. A survey of machine learning researchers and practitioners reveals that GraphXAIN enhances four explainability dimensions: understandability, satisfaction, convincingness, and suitability for communicating model predictions. When combined with another graph explainer method, GraphXAIN further improves trustworthiness, insightfulness, confidence, and usability. Notably, 95% of participants found GraphXAIN to be a valuable addition to the GNN explanation method. By incorporating natural language narratives, our approach serves both graph practitioners and non-expert users by providing clearer and more effective explanations.

In an era where digital threats are increasingly sophisticated, the intersection of Artificial Intelligence and cybersecurity presents both promising defenses and potent dangers. This paper delves into the escalating threat posed by the misuse of AI, specifically through the use of Large Language Models (LLMs). This study details various techniques like the switch method and character play method, which can be exploited by cybercriminals to generate and automate cyber attacks. Through a series of controlled experiments, the paper demonstrates how these models can be manipulated to bypass ethical and privacy safeguards to effectively generate cyber attacks such as social engineering, malicious code, payload generation, and spyware. By testing these AI generated attacks on live systems, the study assesses their effectiveness and the vulnerabilities they exploit, offering a practical perspective on the risks AI poses to critical infrastructure. We also introduce Occupy AI, a customized, finetuned LLM specifically engineered to automate and execute cyberattacks. This specialized AI driven tool is adept at crafting steps and generating executable code for a variety of cyber threats, including phishing, malware injection, and system exploitation. The results underscore the urgency for ethical AI practices, robust cybersecurity measures, and regulatory oversight to mitigate AI related threats. This paper aims to elevate awareness within the cybersecurity community about the evolving digital threat landscape, advocating for proactive defense strategies and responsible AI development to protect against emerging cyber threats.

Measuring User Understanding in Dialogue-based XAI Systems

Dimitry Mindlin, Amelie Sophie Robrecht, Michael Morasch +1

The field of eXplainable Artificial Intelligence (XAI) is increasingly recognizing the need to personalize and/or interactively adapt the explanation to better reflect users' explanation needs. While dialogue-based approaches to XAI have been proposed recently, the state-of-the-art in XAI is still characterized by what we call one-shot, non-personalized and one-way explanations. In contrast, dialogue-based systems that can adapt explanations through interaction with a user promise to be superior to GUI-based or dashboard explanations as they offer a more intuitive way of requesting information. In general, while interactive XAI systems are often evaluated in terms of user satisfaction, there are limited studies that access user's objective model understanding. This is in particular the case for dialogue-based XAI approaches. In this paper, we close this gap by carrying out controlled experiments within a dialogue framework in which we measure understanding of users in three phases by asking them to simulate the predictions of the model they are learning about. By this, we can quantify the level of (improved) understanding w.r.t. how the model works, comparing the state prior, and after the interaction. We further analyze the data to reveal patterns of how the interaction between groups with high vs. low understanding gain differ. Overall, our work thus contributes to our understanding about the effectiveness of XAI approaches.

MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models

Shengkang Wang, Hongzhan Lin, Ziyang Luo +3

Large vision-language models (LVLMs) have significantly improved multimodal reasoning tasks, such as visual question answering and image captioning. These models embed multimodal facts within their parameters, rather than relying on external knowledge bases to store factual information explicitly. However, the content discerned by LVLMs may deviate from factuality due to inherent bias or incorrect inference. To address this issue, we introduce MFC-Bench, a rigorous and comprehensive benchmark designed to evaluate the factual accuracy of LVLMs across three stages of verdict prediction for MFC: Manipulation, Out-of-Context, and Veracity Classification. Through our evaluation on MFC-Bench, we benchmarked a dozen diverse and representative LVLMs, uncovering that current models still fall short in multimodal fact-checking and demonstrate insensitivity to various forms of manipulated content. We hope that MFC-Bench could raise attention to the trustworthy AI potentially assisted by LVLMs in the future. The MFC-Bench and accompanying resources are publicly accessible at https://github.com/wskbest/MFC-Bench, contributing to ongoing research in the multimodal fact-checking field.

In this work we challenge arguments for robot rights on metaphysical, ethical and legal grounds. Metaphysically, we argue that machines are not the kinds of things that may be denied or granted rights. Building on theories of phenomenology and post-Cartesian approaches to cognitive science, we ground our position in the lived reality of actual humans in an increasingly ubiquitously connected, controlled, digitized, and surveilled society. Ethically, we argue that, given machines current and potential harms to the most marginalized in society, limits on (rather than rights for) machines should be at the centre of current AI ethics debate. From a legal perspective, the best analogy to robot rights is not human rights but corporate rights, a highly controversial concept whose most important effect has been the undermining of worker, consumer, and voter rights by advancing the power of capital to exercise outsized influence on politics and law. The idea of robot rights, we conclude, acts as a smoke screen, allowing theorists and futurists to fantasize about benevolently sentient machines with unalterable needs and desires protected by law. While such fantasies have motivated fascinating fiction and art, once they influence legal theory and practice articulating the scope of rights claims, they threaten to immunize from legal accountability the current AI and robotics that is fuelling surveillance capitalism, accelerating environmental destruction, and entrenching injustice and human suffering.

Incorporating Explanations into Human-Machine Interfaces for Trust and Situation Awareness in Autonomous Vehicles

Shahin Atakishiyev, Mohammad Salameh, Randy Goebel

Autonomous vehicles often make complex decisions via machine learning-based predictive models applied to collected sensor data. While this combination of methods provides a foundation for real-time actions, self-driving behavior primarily remains opaque to end users. In this sense, explainability of real-time decisions is a crucial and natural requirement for building trust in autonomous vehicles. Moreover, as autonomous vehicles still cause serious traffic accidents for various reasons, timely conveyance of upcoming hazards to road users can help improve scene understanding and prevent potential risks. Hence, there is also a need to supply autonomous vehicles with user-friendly interfaces for effective human-machine teaming. Motivated by this problem, we study the role of explainable AI and human-machine interface jointly in building trust in vehicle autonomy. We first present a broad context of the explanatory human-machine systems with the "3W1H" (what, whom, when, how) approach. Based on these findings, we present a situation awareness framework for calibrating users' trust in self-driving behavior. Finally, we perform an experiment on our framework, conduct a user study on it, and validate the empirical findings with hypothesis testing.

Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessment

Paraskevas Pegios, Manxi Lin, Nina Weng +6

Obstetric ultrasound image quality is crucial for accurate diagnosis and monitoring of fetal health. However, acquiring high-quality standard planes is difficult, influenced by the sonographer's expertise and factors like the maternal BMI or fetus dynamics. In this work, we explore diffusion-based counterfactual explainable AI to generate realistic, high-quality standard planes from low-quality non-standard ones. Through quantitative and qualitative evaluation, we demonstrate the effectiveness of our approach in generating plausible counterfactuals of increased quality. This shows future promise for enhancing training of clinicians by providing visual feedback and potentially improving standard plane quality and acquisition for downstream diagnosis and monitoring.

Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated Vulnerability Disclosure (CVD) ecosystem in software security. While global efforts to establish frameworks for AI transparency and collaboration are underway, the unique challenges presented by machine learning (ML) models demand a specialized approach. To address this gap, we propose implementing a Coordinated Flaw Disclosure (CFD) framework tailored to the complexities of ML and AI issues. This paper reviews the evolution of ML disclosure practices, from ad hoc reporting to emerging participatory auditing methods, and compares them with cybersecurity norms. Our framework introduces innovations such as extended model cards, dynamic scope expansion, an independent adjudication panel, and an automated verification process. We also outline a forthcoming real-world pilot of CFD. We argue that CFD could significantly enhance public trust in AI systems. By balancing organizational and community interests, CFD aims to improve AI accountability in a rapidly evolving technological landscape.

The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE). However, due to their black-box nature, these promising AI-driven SE models are still far from being deployed in practice. This lack of explainability poses unwanted risks for their applications in critical tasks, such as vulnerability detection, where decision-making transparency is of paramount importance. This paper endeavors to elucidate this interdisciplinary domain by presenting a systematic literature review of approaches that aim to improve the explainability of AI models within the context of SE. The review canvasses work appearing in the most prominent SE & AI conferences and journals, and spans 108 papers across 23 unique SE tasks. Based on three key Research Questions (RQs), we aim to (1) summarize the SE tasks where XAI techniques have shown success to date; (2) classify and analyze different XAI techniques; and (3) investigate existing evaluation approaches. Based on our findings, we identified a set of challenges remaining to be addressed in existing studies, together with a set of guidelines highlighting potential opportunities we deemed appropriate and important for future work.

Skin cancer is a serious worldwide health issue, precise and early detection is essential for better patient outcomes and effective treatment. In this research, we use modern deep learning methods and explainable artificial intelligence (XAI) approaches to address the problem of skin cancer detection. To categorize skin lesions, we employ four cutting-edge pre-trained models: XceptionNet, EfficientNetV2S, InceptionResNetV2, and EfficientNetV2M. Image augmentation approaches are used to reduce class imbalance and improve the generalization capabilities of our models. Our models decision-making process can be clarified because of the implementation of explainable artificial intelligence (XAI). In the medical field, interpretability is essential to establish credibility and make it easier to implement AI driven diagnostic technologies into clinical workflows. We determined the XceptionNet architecture to be the best performing model, achieving an accuracy of 88.72%. Our study shows how deep learning and explainable artificial intelligence (XAI) can improve skin cancer diagnosis, laying the groundwork for future developments in medical image analysis. These technologies ability to allow for early and accurate detection could enhance patient care, lower healthcare costs, and raise the survival rates for those with skin cancer. Source Code: https://github.com/Faysal-MD/An-Interpretable-Deep-Learning?Approach-for-Skin-Cancer-Categorization-IEEE2023