Research Papers

Recently, uncertainty-aware deep learning methods for multiclass labeling problems have been developed that provide calibrated class prediction probabilities and out-of-distribution (OOD) indicators, letting machine learning (ML) consumers and engineers gauge a model's confidence in its predictions. However, this extra neural network prediction information is challenging to scalably convey visually for arbitrary data sources under multiple uncertainty contexts. To address these challenges, we present ScatterUQ, an interactive system that provides targeted visualizations to allow users to better understand model performance in context-driven uncertainty settings. ScatterUQ leverages recent advances in distance-aware neural networks, together with dimensionality reduction techniques, to construct robust, 2-D scatter plots explaining why a model predicts a test example to be (1) in-distribution and of a particular class, (2) in-distribution but unsure of the class, and (3) out-of-distribution. ML consumers and engineers can visually compare the salient features of test samples with training examples through the use of a ``hover callback'' to understand model uncertainty performance and decide follow up courses of action. We demonstrate the effectiveness of ScatterUQ to explain model uncertainty for a multiclass image classification on a distance-aware neural network trained on Fashion-MNIST and tested on Fashion-MNIST (in distribution) and MNIST digits (out of distribution), as well as a deep learning model for a cyber dataset. We quantitatively evaluate dimensionality reduction techniques to optimize our contextually driven UQ visualizations. Our results indicate that the ScatterUQ system should scale to arbitrary, multiclass datasets. Our code is available at https://github.com/mit-ll-responsible-ai/equine-webapp

The massive volume of online information along with the issue of misinformation has spurred active research in the automation of fact-checking. Like fact-checking by human experts, it is not enough for an automated fact-checker to just be accurate, but also be able to inform and convince the user of the validity of its predictions. This becomes viable with explainable artificial intelligence (XAI). In this work, we conduct a study of XAI fact-checkers involving 180 participants to determine how users' actions towards news and their attitudes towards explanations are affected by the XAI. Our results suggest that XAI has limited effects on users' agreement with the veracity prediction of the automated fact-checker and on their intent to share news. However, XAI nudges users towards forming uniform judgments of news veracity, thereby signaling their reliance on the explanations. We also found polarizing preferences towards XAI and raise several design considerations on them.

The field of Explainable Artificial Intelligence (XAI) aims to improve the interpretability of black-box machine learning models. Building a heatmap based on the importance value of input features is a popular method for explaining the underlying functions of such models in producing their predictions. Heatmaps are almost understandable to humans, yet they are not without flaws. Non-expert users, for example, may not fully understand the logic of heatmaps (the logic in which relevant pixels to the model's prediction are highlighted with different intensities or colors). Additionally, objects and regions of the input image that are relevant to the model prediction are frequently not entirely differentiated by heatmaps. In this paper, we propose a framework called TbExplain that employs XAI techniques and a pre-trained object detector to present text-based explanations of scene classification models. Moreover, TbExplain incorporates a novel method to correct predictions and textually explain them based on the statistics of objects in the input image when the initial prediction is unreliable. To assess the trustworthiness and validity of the text-based explanations, we conducted a qualitative experiment, and the findings indicated that these explanations are sufficiently reliable. Furthermore, our quantitative and qualitative experiments on TbExplain with scene classification datasets reveal an improvement in classification accuracy over ResNet variants.

This paper investigates the impact of feature encoding techniques on the explainability of XAI (Explainable Artificial Intelligence) algorithms. Using a malware classification dataset, we trained an XGBoost model and compared the performance of two feature encoding methods: Label Encoding (LE) and One Hot Encoding (OHE). Our findings reveal a marginal performance loss when using OHE instead of LE. However, the more detailed explanations provided by OHE compensated for this loss. We observed that OHE enables deeper exploration of details in both global and local contexts, facilitating more comprehensive answers. Additionally, we observed that using OHE resulted in smaller explanation files and reduced analysis time for human analysts. These findings emphasize the significance of considering feature encoding techniques in XAI research and suggest potential for further exploration by incorporating additional encoding methods and innovative visualization approaches.

Unmanned aerial vehicles (UAVs) have gained popularity due to their flexible mobility, on-demand deployment, and the ability to establish high probability line-of-sight wireless communication. As a result, UAVs have been extensively used as aerial base stations (ABSs) to supplement ground-based cellular networks for various applications. However, existing UAV-assisted communication schemes mainly focus on trajectory optimization and power allocation, while ignoring the issue of collision avoidance during UAV flight. To address this issue, this paper proposes an interpretable UAV-assisted communication scheme that decomposes reliable UAV services into two sub-problems. The first is the constrained UAV coordinates and power allocation problem, which is solved using the Dueling Double DQN (D3QN) method. The second is the constrained UAV collision avoidance and trajectory optimization problem, which is addressed through the Monte Carlo tree search (MCTS) method. This approach ensures both reliable and efficient operation of UAVs. Moreover, we propose a scalable interpretable artificial intelligence (XAI) framework that enables more transparent and reliable system decisions. The proposed scheme's interpretability generates explainable and trustworthy results, making it easier to comprehend, validate, and control UAV-assisted communication solutions. Through extensive experiments, we demonstrate that our proposed algorithm outperforms existing techniques in terms of performance and generalization. The proposed model improves the reliability, efficiency, and safety of UAV-assisted communication systems, making it a promising solution for future UAV-assisted communication applications

Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings

Lukas Klein, João B. S. Carvalho, Mennatallah El-Assady +3

Explainable AI aims to render model behavior understandable by humans, which can be seen as an intermediate step in extracting causal relations from correlative patterns. Due to the high risk of possible fatal decisions in image-based clinical diagnostics, it is necessary to integrate explainable AI into these safety-critical systems. Current explanatory methods typically assign attribution scores to pixel regions in the input image, indicating their importance for a model's decision. However, they fall short when explaining why a visual feature is used. We propose a framework that utilizes interpretable disentangled representations for downstream-task prediction. Through visualizing the disentangled representations, we enable experts to investigate possible causation effects by leveraging their domain knowledge. Additionally, we deploy a multi-path attribution mapping for enriching and validating explanations. We demonstrate the effectiveness of our approach on a synthetic benchmark suite and two medical datasets. We show that the framework not only acts as a catalyst for causal relation extraction but also enhances model robustness by enabling shortcut detection without the need for testing under distribution shifts.

In this paper, we introduce the idea of decomposing the residuals of regression with respect to the data instances instead of features. This allows us to determine the effects of each individual instance on the model and each other, and in doing so makes for a model-agnostic method of identifying instances of interest. In doing so, we can also determine the appropriateness of the model and data in the wider context of a given study. The paper focuses on the possible applications that such a framework brings to the relatively unexplored field of instance analysis in the context of Explainable AI tasks.

Neural networks have shown remarkable performance in computer vision, but their deployment in numerous scientific and technical fields is challenging due to their black-box nature. Scientists and practitioners need to evaluate the reliability of a decision, i.e., to know simultaneously if a model relies on the relevant features and whether these features are robust to image corruptions. Existing attribution methods aim to provide human-understandable explanations by highlighting important regions in the image domain, but fail to fully characterize a decision process's reliability. To bridge this gap, we introduce the Wavelet sCale Attribution Method (WCAM), a generalization of attribution from the pixel domain to the space-scale domain using wavelet transforms. Attribution in the wavelet domain reveals where and on what scales the model focuses, thus enabling us to assess whether a decision is reliable. Our code is accessible here: \url{https://github.com/gabrielkasmi/spectral-attribution}.

The Representational Status of Deep Learning Models

Eamon Duede

This paper aims to clarify the representational status of Deep Learning Models (DLMs). While commonly referred to as 'representations', what this entails is ambiguous due to a conflation of functional and relational conceptions of representation. This paper argues that while DLMs represent their targets in a relational sense, in general, we have no good reason to believe that DLMs encode locally semantically decomposable representations of their targets. That is, the representational capacity these models have is largely global, rather than decomposable into stable, local subrepresentations. This result has immediate implications for explainable AI (XAI) and directs attention toward exploring the global relational nature of deep learning representations and their relationship both to models more generally to understand their potential role in future scientific inquiry.

Purpose Predicting the progression of MCI to Alzheimer's disease is an important step in reducing the progression of the disease. Therefore, many methods have been introduced for this task based on deep learning. Among these approaches, the methods based on ROIs are in a good position in terms of accuracy and complexity. In these techniques, some specific parts of the brain are extracted as ROI manually for all of the patients. Extracting ROI manually is time-consuming and its results depend on human expertness and precision. Method To overcome these limitations, we propose a novel smart method for detecting ROIs automatically based on Explainable AI using Grad-Cam and a 3DCNN model that extracts ROIs per patient. After extracting the ROIs automatically, Alzheimer's disease is predicted using extracted ROI-based 3D CNN. Results We implement our method on 176 MCI patients of the famous ADNI dataset and obtain remarkable results compared to the state-of-the-art methods. The accuracy acquired using 5-fold cross-validation is 98.6 and the AUC is 1. We also compare the results of the ROI-based method with the whole brain-based method. The results show that the performance is impressively increased. Conclusion The experimental results show that the proposed smart ROI extraction, which extracts the ROIs automatically, performs well for Alzheimer's disease prediction. The proposed method can also be used for Alzheimer's disease classification and diagnosis.

In this expository article we highlight the relevance of explanations for artificial intelligence, in general, and for the newer developments in {\em explainable AI}, referring to origins and connections of and among different approaches. We describe in simple terms, explanations in data management and machine learning that are based on attribution-scores, and counterfactuals as found in the area of causality. We elaborate on the importance of logical reasoning when dealing with counterfactuals, and their use for score computation.

As security communities brace for the emerging social automation based threats, we examine the mechanisms of developing situation awareness in cyberspace and the governance issues that socialbots bring into this existing paradigm of cyber situation awareness. We point out that an organisation's situation awareness in cyberspace is a phenomena fundamentally distinct from the original conception of situation awareness, requiring continuous data exchange and knowledge management where the standard implementation mechanisms require significant policy attention in light of threats like malicious social automation. We conceptualise Cyberspace Awareness as a socio-technical phenomena with Syntactic, Semantic, and Operatic dimensions - each subject to a number of stressors which are exacerbated under social automation based threats. The paper contributes to the ideas of situational awareness in cyberspace, and characterises the challenges therein around tackling the increasingly social and often pervasive, automation in cyber threat environments.