Research Papers

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of SAEs to Vision-Language Models (VLMs), such as CLIP, and introduce a comprehensive framework for evaluating monosemanticity at the neuron-level in visual representations. To ensure that our evaluation aligns with human perception, we propose a benchmark derived from a large-scale user study. Our experimental results reveal that SAEs trained on VLMs significantly enhance the monosemanticity of individual neurons, with sparsity and wide latents being the most influential factors. Further, we demonstrate that applying SAE interventions on CLIP's vision encoder directly steers multimodal LLM outputs (e.g., LLaVA), without any modifications to the underlying language model. These findings emphasize the practicality and efficacy of SAEs as an unsupervised tool for enhancing both interpretability and control of VLMs. Code and benchmark data are available at https://github.com/ExplainableML/sae-for-vlm.

Gradient based Feature Attribution in Explainable AI: A Technical Review

Yongjie Wang, Tong Zhang, Xu Guo +1

The surge in black-box AI models has prompted the need to explain the internal mechanism and justify their reliability, especially in high-stakes applications, such as healthcare and autonomous driving. Due to the lack of a rigorous definition of explainable AI (XAI), a plethora of research related to explainability, interpretability, and transparency has been developed to explain and analyze the model from various perspectives. Consequently, with an exhaustive list of papers, it becomes challenging to have a comprehensive overview of XAI research from all aspects. Considering the popularity of neural networks in AI research, we narrow our focus to a specific area of XAI research: gradient based explanations, which can be directly adopted for neural network models. In this review, we systematically explore gradient based explanation methods to date and introduce a novel taxonomy to categorize them into four distinct classes. Then, we present the essence of technique details in chronological order and underscore the evolution of algorithms. Next, we introduce both human and quantitative evaluations to measure algorithm performance. More importantly, we demonstrate the general challenges in XAI and specific challenges in gradient based explanations. We hope that this survey can help researchers understand state-of-the-art progress and their corresponding disadvantages, which could spark their interest in addressing these issues in future work.

In the past few years, artificial intelligence (AI) techniques have been implemented in almost all verticals of human life. However, the results generated from the AI models often lag explainability. AI models often appear as a blackbox wherein developers are unable to explain or trace back the reasoning behind a specific decision. Explainable AI (XAI) is a rapid growing field of research which helps to extract information and also visualize the results generated with an optimum transparency. The present study provides and extensive review of the use of XAI in cybersecurity. Cybersecurity enables protection of systems, networks and programs from different types of attacks. The use of XAI has immense potential in predicting such attacks. The paper provides a brief overview on cybersecurity and the various forms of attack. Then the use of traditional AI techniques and its associated challenges are discussed which opens its doors towards use of XAI in various applications. The XAI implementations of various research projects and industry are also presented. Finally, the lessons learnt from these applications are highlighted which act as a guide for future scope of research.

Machine learning (ML) and Deep Learning (DL) methods are being adopted rapidly, especially in computer network security, such as fraud detection, network anomaly detection, intrusion detection, and much more. However, the lack of transparency of ML and DL based models is a major obstacle to their implementation and criticized due to its black-box nature, even with such tremendous results. Explainable Artificial Intelligence (XAI) is a promising area that can improve the trustworthiness of these models by giving explanations and interpreting its output. If the internal working of the ML and DL based models is understandable, then it can further help to improve its performance. The objective of this paper is to show that how XAI can be used to interpret the results of the DL model, the autoencoder in this case. And, based on the interpretation, we improved its performance for computer network anomaly detection. The kernel SHAP method, which is based on the shapley values, is used as a novel feature selection technique. This method is used to identify only those features that are actually causing the anomalous behaviour of the set of attack/anomaly instances. Later, these feature sets are used to train and validate the autoencoder but on benign data only. Finally, the built SHAP_Model outperformed the other two models proposed based on the feature selection method. This whole experiment is conducted on the subset of the latest CICIDS2017 network dataset. The overall accuracy and AUC of SHAP_Model is 94% and 0.969, respectively.

Predictive modeling in healthcare continues to be an active actuarial research topic as more insurance companies aim to maximize the potential of Machine Learning approaches to increase their productivity and efficiency. In this paper, the authors deployed three regression-based ensemble ML models that combine variations of decision trees through Extreme Gradient Boosting, Gradient-boosting Machine, and Random Forest) methods in predicting medical insurance costs. Explainable Artificial Intelligence methods SHapley Additive exPlanations and Individual Conditional Expectation plots were deployed to discover and explain the key determinant factors that influence medical insurance premium prices in the dataset. The dataset used comprised 986 records and is publicly available in the KAGGLE repository. The models were evaluated using four performance evaluation metrics, including R-squared, Mean Absolute Error, Root Mean Squared Error, and Mean Absolute Percentage Error. The results show that all models produced impressive outcomes; however, the XGBoost model achieved a better overall performance although it also expanded more computational resources, while the RF model recorded a lesser prediction error and consumed far fewer computing resources than the XGBoost model. Furthermore, we compared the outcome of both XAi methods in identifying the key determinant features that influenced the PremiumPrices for each model and whereas both XAi methods produced similar outcomes, we found that the ICE plots showed in more detail the interactions between each variable than the SHAP analysis which seemed to be more high-level. It is the aim of the authors that the contributions of this study will help policymakers, insurers, and potential medical insurance buyers in their decision-making process for selecting the right policies that meet their specific needs.

In the past decade, the deployment of deep learning (Artificial Intelligence (AI)) methods has become pervasive across a spectrum of real-world applications, often in safety-critical contexts. This comprehensive research article rigorously investigates the ethical dimensions intricately linked to the rapid evolution of AI technologies, with a particular focus on the healthcare domain. Delving deeply, it explores a multitude of facets including transparency, adept data management, human oversight, educational imperatives, and international collaboration within the realm of AI advancement. Central to this article is the proposition of a conscientious AI framework, meticulously crafted to accentuate values of transparency, equity, answerability, and a human-centric orientation. The second contribution of the article is the in-depth and thorough discussion of the limitations inherent to AI systems. It astutely identifies potential biases and the intricate challenges of navigating multifaceted contexts. Lastly, the article unequivocally accentuates the pressing need for globally standardized AI ethics principles and frameworks. Simultaneously, it aptly illustrates the adaptability of the ethical framework proposed herein, positioned skillfully to surmount emergent challenges.

Metaverse is expected to emerge as a new paradigm for the next-generation Internet, providing fully immersive and personalised experiences to socialize, work, and play in self-sustaining and hyper-spatio-temporal virtual world(s). The advancements in different technologies like augmented reality, virtual reality, extended reality (XR), artificial intelligence (AI), and 5G/6G communication will be the key enablers behind the realization of AI-XR metaverse applications. While AI itself has many potential applications in the aforementioned technologies (e.g., avatar generation, network optimization, etc.), ensuring the security of AI in critical applications like AI-XR metaverse applications is profoundly crucial to avoid undesirable actions that could undermine users' privacy and safety, consequently putting their lives in danger. To this end, we attempt to analyze the security, privacy, and trustworthiness aspects associated with the use of various AI techniques in AI-XR metaverse applications. Specifically, we discuss numerous such challenges and present a taxonomy of potential solutions that could be leveraged to develop secure, private, robust, and trustworthy AI-XR applications. To highlight the real implications of AI-associated adversarial threats, we designed a metaverse-specific case study and analyzed it through the adversarial lens. Finally, we elaborate upon various open issues that require further research interest from the community.

Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks. We identify 3 cybersecurity stakeholders, i.e., model users, designers, and adversaries, who utilize XAI for 4 distinct objectives within an ML pipeline, namely 1) XAI-enabled user assistance, 2) XAI-enabled model verification, 3) explanation verification & robustness, and 4) offensive use of explanations. Our analysis of the literature indicates that many of the XAI applications are designed with little understanding of how they might be integrated into analyst workflows -- user studies for explanation evaluation are conducted in only 14% of the cases. The security literature sometimes also fails to disentangle the role of the various stakeholders, e.g., by providing explanations to model users and designers while also exposing them to adversaries. Additionally, the role of model designers is particularly minimized in the security literature. To this end, we present an illustrative tutorial for model designers, demonstrating how XAI can help with model verification. We also discuss scenarios where interpretability by design may be a better alternative. The systematization and the tutorial enable us to challenge several assumptions, and present open problems that can help shape the future of XAI research within cybersecurity.

Explainability in Music Recommender Systems

Darius Afchar, Alessandro B. Melchiorre, Markus Schedl +3

The most common way to listen to recorded music nowadays is via streaming platforms which provide access to tens of millions of tracks. To assist users in effectively browsing these large catalogs, the integration of Music Recommender Systems (MRSs) has become essential. Current real-world MRSs are often quite complex and optimized for recommendation accuracy. They combine several building blocks based on collaborative filtering and content-based recommendation. This complexity can hinder the ability to explain recommendations to end users, which is particularly important for recommendations perceived as unexpected or inappropriate. While pure recommendation performance often correlates with user satisfaction, explainability has a positive impact on other factors such as trust and forgiveness, which are ultimately essential to maintain user loyalty. In this article, we discuss how explainability can be addressed in the context of MRSs. We provide perspectives on how explainability could improve music recommendation algorithms and enhance user experience. First, we review common dimensions and goals of recommenders' explainability and in general of eXplainable Artificial Intelligence (XAI), and elaborate on the extent to which these apply -- or need to be adapted -- to the specific characteristics of music consumption and recommendation. Then, we show how explainability components can be integrated within a MRS and in what form explanations can be provided. Since the evaluation of explanation quality is decoupled from pure accuracy-based evaluation criteria, we also discuss requirements and strategies for evaluating explanations of music recommendations. Finally, we describe the current challenges for introducing explainability within a large-scale industrial music recommender system and provide research perspectives.

Conceptualising Contestability: Perspectives on Contesting Algorithmic Decisions

Henrietta Lyons, Eduardo Velloso, Tim Miller

As the use of algorithmic systems in high-stakes decision-making increases, the ability to contest algorithmic decisions is being recognised as an important safeguard for individuals. Yet, there is little guidance on what `contestability'--the ability to contest decisions--in relation to algorithmic decision-making requires. Recent research presents different conceptualisations of contestability in algorithmic decision-making. We contribute to this growing body of work by describing and analysing the perspectives of people and organisations who made submissions in response to Australia's proposed `AI Ethics Framework', the first framework of its kind to include `contestability' as a core ethical principle. Our findings reveal that while the nature of contestability is disputed, it is seen as a way to protect individuals, and it resembles contestability in relation to human decision-making. We reflect on and discuss the implications of these findings.

The integration of artificial intelligence (AI) in educational measurement has revolutionized assessment methods, enabling automated scoring, rapid content analysis, and personalized feedback through machine learning and natural language processing. These advancements provide timely, consistent feedback and valuable insights into student performance, thereby enhancing the assessment experience. However, the deployment of AI in education also raises significant ethical concerns regarding validity, reliability, transparency, fairness, and equity. Issues such as algorithmic bias and the opacity of AI decision-making processes pose risks of perpetuating inequalities and affecting assessment outcomes. Responding to these concerns, various stakeholders, including educators, policymakers, and organizations, have developed guidelines to ensure ethical AI use in education. The National Council of Measurement in Education's Special Interest Group on AI in Measurement and Education (AIME) also focuses on establishing ethical standards and advancing research in this area. In this paper, a diverse group of AIME members examines the ethical implications of AI-powered tools in educational measurement, explores significant challenges such as automation bias and environmental impact, and proposes solutions to ensure AI's responsible and effective use in education.

Although AI is transforming the world, there are serious concerns about its ability to behave and make decisions responsibly. Many ethical regulations, principles, and frameworks for responsible AI have been issued recently. However, they are high level and difficult to put into practice. On the other hand, most AI researchers focus on algorithmic solutions, while the responsible AI challenges actually crosscut the entire engineering lifecycle and components of AI systems. To close the gap in operationalizing responsible AI, this paper aims to develop a roadmap on software engineering for responsible AI. The roadmap focuses on (i) establishing multi-level governance for responsible AI systems, (ii) setting up the development processes incorporating process-oriented practices for responsible AI systems, and (iii) building responsible-AI-by-design into AI systems through system-level architectural style, patterns and techniques.