Research Papers

NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attacks

Wenkai Tan, Justus Renkhoff, Alvaro Velasquez +7

Deep Learning (DL) and Deep Neural Networks (DNNs) are widely used in various domains. However, adversarial attacks can easily mislead a neural network and lead to wrong decisions. Defense mechanisms are highly preferred in safety-critical applications. In this paper, firstly, we use the gradient class activation map (GradCAM) to analyze the behavior deviation of the VGG-16 network when its inputs are mixed with adversarial perturbation or Gaussian noise. In particular, our method can locate vulnerable layers that are sensitive to adversarial perturbation and Gaussian noise. We also show that the behavior deviation of vulnerable layers can be used to detect adversarial examples. Secondly, we propose a novel NoiseCAM algorithm that integrates information from globally and pixel-level weighted class activation maps. Our algorithm is susceptible to adversarial perturbations and will not respond to Gaussian random noise mixed in the inputs. Third, we compare detecting adversarial examples using both behavior deviation and NoiseCAM, and we show that NoiseCAM outperforms behavior deviation modeling in its overall performance. Our work could provide a useful tool to defend against certain adversarial attacks on deep neural networks.

Out-of-distribution detection is one of the most critical issue in the deployment of machine learning. The data analyst must assure that data in operation should be compliant with the training phase as well as understand if the environment has changed in a way that autonomous decisions would not be safe anymore. The method of the paper is based on eXplainable Artificial Intelligence (XAI); it takes into account different metrics to identify any resemblance between in-distribution and out of, as seen by the XAI model. The approach is non-parametric and distributional assumption free. The validation over complex scenarios (predictive maintenance, vehicle platooning, covert channels in cybersecurity) corroborates both precision in detection and evaluation of training-operation conditions proximity. Results are available via open source and open data at the following link: https://github.com/giacomo97cnr/Rule-based-ODD.

Modeling Reliance on XAI Indicating Its Purpose and Attention

Akihiro Maehigashi, Yosuke Fukuchi, Seiji Yamada

This study used XAI, which shows its purposes and attention as explanations of its process, and investigated how these explanations affect human trust in and use of AI. In this study, we generated heat maps indicating AI attention, conducted Experiment 1 to confirm the validity of the interpretability of the heat maps, and conducted Experiment 2 to investigate the effects of the purpose and heat maps in terms of reliance (depending on AI) and compliance (accepting answers of AI). The results of structural equation modeling (SEM) analyses showed that (1) displaying the purpose of AI positively and negatively influenced trust depending on the types of AI usage, reliance or compliance, and task difficulty, (2) just displaying the heat maps negatively influenced trust in a more difficult task, and (3) the heat maps positively influenced trust according to their interpretability in a more difficult task.

The increasing complexity of AI systems has led to the growth of the field of Explainable Artificial Intelligence (XAI), which aims to provide explanations and justifications for the outputs of AI algorithms. While there is considerable demand for XAI, there remains a scarcity of studies aimed at comprehensively understanding the practical distinctions among different methods and effectively aligning each method with users individual needs, and ideally, offer a mapping function which can map each user with its specific needs to a method of explainability. This study endeavors to bridge this gap by conducting a thorough review of extant research in XAI, with a specific focus on Explainable Machine Learning (XML), and a keen eye on user needs. Our main objective is to offer a classification of XAI methods within the realm of XML, categorizing current works into three distinct domains: philosophy, theory, and practice, and providing a critical review for each category. Moreover, our study seeks to facilitate the connection between XAI users and the most suitable methods for them and tailor explanations to meet their specific needs by proposing a mapping function that take to account users and their desired properties and suggest an XAI method to them. This entails an examination of prevalent XAI approaches and an evaluation of their properties. The primary outcome of this study is the formulation of a clear and concise strategy for selecting the optimal XAI method to achieve a given goal, all while delivering personalized explanations tailored to individual users.

Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and finance

Dangxing Chen, Luyao Zhang

Algorithm fairness in the application of artificial intelligence (AI) is essential for a better society. As the foundational axiom of social mechanisms, fairness consists of multiple facets. Although the machine learning (ML) community has focused on intersectionality as a matter of statistical parity, especially in discrimination issues, an emerging body of literature addresses another facet -- monotonicity. Based on domain expertise, monotonicity plays a vital role in numerous fairness-related areas, where violations could misguide human decisions and lead to disastrous consequences. In this paper, we first systematically evaluate the significance of applying monotonic neural additive models (MNAMs), which use a fairness-aware ML algorithm to enforce both individual and pairwise monotonicity principles, for the fairness of AI ethics and society. We have found, through a hybrid method of theoretical reasoning, simulation, and extensive empirical analysis, that considering monotonicity axioms is essential in all areas of fairness, including criminology, education, health care, and finance. Our research contributes to the interdisciplinary research at the interface of AI ethics, explainable AI (XAI), and human-computer interactions (HCIs). By evidencing the catastrophic consequences if monotonicity is not met, we address the significance of monotonicity requirements in AI applications. Furthermore, we demonstrate that MNAMs are an effective fairness-aware ML approach by imposing monotonicity restrictions integrating human intelligence.

Human activity recognition (HAR) using IMU sensors, namely accelerometer and gyroscope, has several applications in smart homes, healthcare and human-machine interface systems. In practice, the IMU-based HAR system is expected to encounter variations in measurement due to sensor degradation, alien environment or sensor noise and will be subjected to unknown activities. In view of practical deployment of the solution, analysis of statistical confidence over the activity class score are important metrics. In this paper, we therefore propose XAI-BayesHAR, an integrated Bayesian framework, that improves the overall activity classification accuracy of IMU-based HAR solutions by recursively tracking the feature embedding vector and its associated uncertainty via Kalman filter. Additionally, XAI-BayesHAR acts as an out of data distribution (OOD) detector using the predictive uncertainty which help to evaluate and detect alien input data distribution. Furthermore, Shapley value-based performance of the proposed framework is also evaluated to understand the importance of the feature embedding vector and accordingly used for model compression

With the rising adoption of Machine Learning across the domains like banking, pharmaceutical, ed-tech, etc, it has become utmost important to adopt responsible AI methods to ensure models are not unfairly discriminating against any group. Given the lack of clean training data, generative adversarial techniques are preferred to generate synthetic data with several state-of-the-art architectures readily available across various domains from unstructured data such as text, images to structured datasets modelling fraud detection and many more. These techniques overcome several challenges such as class imbalance, limited training data, restricted access to data due to privacy issues. Existing work focusing on generating fair data either works for a certain GAN architecture or is very difficult to tune across the GANs. In this paper, we propose a pipeline to generate fairer synthetic data independent of the GAN architecture. The proposed paper utilizes a pre-processing algorithm to identify and remove bias inducing samples. In particular, we claim that while generating synthetic data most GANs amplify bias present in the training data but by removing these bias inducing samples, GANs essentially focuses more on real informative samples. Our experimental evaluation on two open-source datasets demonstrates how the proposed pipeline is generating fair data along with improved performance in some cases.

On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations

Julia El Zini, Mohamad Mansour, Basel Mousi +1

Current Explainable AI (ExAI) methods, especially in the NLP field, are conducted on various datasets by employing different metrics to evaluate several aspects. The lack of a common evaluation framework is hindering the progress tracking of such methods and their wider adoption. In this work, inspired by offline information retrieval, we propose different metrics and techniques to evaluate the explainability of SA models from two angles. First, we evaluate the strength of the extracted "rationales" in faithfully explaining the predicted outcome. Second, we measure the agreement between ExAI methods and human judgment on a homegrown dataset1 to reflect on the rationales plausibility. Our conducted experiments comprise four dimensions: (1) the underlying architectures of SA models, (2) the approach followed by the ExAI method, (3) the reasoning difficulty, and (4) the homogeneity of the ground-truth rationales. We empirically demonstrate that anchors explanations are more aligned with the human judgment and can be more confident in extracting supporting rationales. As can be foreseen, the reasoning complexity of sentiment is shown to thwart ExAI methods from extracting supporting evidence. Moreover, a remarkable discrepancy is discerned between the results of different explainability methods on the various architectures suggesting the need for consolidation to observe enhanced performance. Predominantly, transformers are shown to exhibit better explainability than convolutional and recurrent architectures. Our work paves the way towards designing more interpretable NLP models and enabling a common evaluation ground for their relative strengths and robustness.

OAK4XAI: Model towards Out-Of-Box eXplainable Artificial Intelligence for Digital Agriculture

Quoc Hung Ngo, Tahar Kechadi, Nhien-An Le-Khac

Recent machine learning approaches have been effective in Artificial Intelligence (AI) applications. They produce robust results with a high level of accuracy. However, most of these techniques do not provide human-understandable explanations for supporting their results and decisions. They usually act as black boxes, and it is not easy to understand how decisions have been made. Explainable Artificial Intelligence (XAI), which has received much interest recently, tries to provide human-understandable explanations for decision-making and trained AI models. For instance, in digital agriculture, related domains often present peculiar or input features with no link to background knowledge. The application of the data mining process on agricultural data leads to results (knowledge), which are difficult to explain. In this paper, we propose a knowledge map model and an ontology design as an XAI framework (OAK4XAI) to deal with this issue. The framework does not only consider the data analysis part of the process, but it takes into account the semantics aspect of the domain knowledge via an ontology and a knowledge map model, provided as modules of the framework. Many ongoing XAI studies aim to provide accurate and verbalizable accounts for how given feature values contribute to model decisions. The proposed approach, however, focuses on providing consistent information and definitions of concepts, algorithms, and values involved in the data mining models. We built an Agriculture Computing Ontology (AgriComO) to explain the knowledge mined in agriculture. AgriComO has a well-designed structure and includes a wide range of concepts and transformations suitable for agriculture and computing domains.

The Convolutional Neural Network (CNN) is a widely used deep learning architecture for computer vision. However, its black box nature makes it difficult to interpret the behavior of the model. To mitigate this issue, AI practitioners have explored explainable AI methods like Class Activation Map (CAM) and Grad-CAM. Although these methods have shown promise, they are limited by architectural constraints or the burden of gradient computing. To overcome this issue, Score-CAM and Ablation-CAM have been proposed as gradient-free methods, but they have longer execution times compared to CAM or Grad-CAM based methods, making them unsuitable for real-world solution though they resolved gradient related issues and enabled inference mode XAI. To address this challenge, we propose a fast gradient-free Reciprocal CAM (Recipro-CAM) method. Our approach involves spatially masking the extracted feature maps to exploit the correlation between activation maps and network predictions for target classes. Our proposed method has yielded promising results, outperforming current state-of-the-art method in the Average Drop-Coherence-Complexity (ADCC) metric by $1.78 \%$ to $3.72 \%$, excluding VGG-16 backbone. Moreover, Recipro-CAM generates saliency maps at a similar rate to Grad-CAM and is approximately $148$ times faster than Score-CAM. The source code for Recipro-CAM is available in our data analysis framework.

The advance of Machine Learning (ML) has led to a strong interest in this technology to support decision making. While complex ML models provide predictions that are often more accurate than those of traditional tools, such models often hide the reasoning behind the prediction from their users, which can lead to lower adoption and lack of insight. Motivated by this tension, research has put forth Explainable Artificial Intelligence (XAI) techniques that uncover patterns discovered by ML. Despite the high hopes in both ML and XAI, there is little empirical evidence of the benefits to traditional businesses. To this end, we analyze data on 220,185 customers of an energy retailer, predict cross-purchases with up to 86% correctness (AUC), and show that the XAI method SHAP provides explanations that hold for actual buyers. We further outline implications for research in information systems, XAI, and relationship marketing.

"Explanation" is Not a Technical Term: The Problem of Ambiguity in XAI

Leilani H. Gilpin, Andrew R. Paley, Mohammed A. Alam +2

There is broad agreement that Artificial Intelligence (AI) systems, particularly those using Machine Learning (ML), should be able to "explain" their behavior. Unfortunately, there is little agreement as to what constitutes an "explanation." This has caused a disconnect between the explanations that systems produce in service of explainable Artificial Intelligence (XAI) and those explanations that users and other audiences actually need, which should be defined by the full spectrum of functional roles, audiences, and capabilities for explanation. In this paper, we explore the features of explanations and how to use those features in evaluating their utility. We focus on the requirements for explanations defined by their functional role, the knowledge states of users who are trying to understand them, and the availability of the information needed to generate them. Further, we discuss the risk of XAI enabling trust in systems without establishing their trustworthiness and define a critical next step for the field of XAI to establish metrics to guide and ground the utility of system-generated explanations.