Research Papers

A key drawback to using a Open Source third-party library is the risk of introducing malicious attacks. In recently times, these threats have taken a new form, when maintainers turn their Open Source libraries into protestware. This is defined as software containing political messages delivered through these libraries, which can either be malicious or benign. Since developers are willing to freely open-up their software to these libraries, much trust and responsibility are placed on the maintainers to ensure that the library does what it promises to do. Using different frameworks commonly used in AI ethics, we illustrate how an open-source maintainer's decision to protest is influenced by different stakeholders (viz., their membership in the OSS community, their personal views, financial motivations, social status, and moral viewpoints), making protestware a multifaceted and intricate matter.

This article appears as chapter 21 of Prince (2023, Understanding Deep Learning); a complete draft of the textbook is available here: http://udlbook.com. This chapter considers potential harms arising from the design and use of AI systems. These include algorithmic bias, lack of explainability, data privacy violations, militarization, fraud, and environmental concerns. The aim is not to provide advice on being more ethical. Instead, the goal is to express ideas and start conversations in key areas that have received attention in philosophy, political science, and the broader social sciences.

This paper argues that Machine Learning (ML) algorithms must be educated. ML-trained algorithms moral decisions are ubiquitous in human society. Sometimes reverting the societal advances governments, NGOs and civil society have achieved with great effort in the last decades or are yet on the path to be achieved. While their decisions have an incommensurable impact on human societies, these algorithms are within the least educated agents known (data incomplete, un-inclusive, or biased). ML algorithms are not something separate from our human idiosyncrasy but an enactment of our most implicit prejudices and biases. Some research is devoted to responsibility assignment as a strategy to tackle immoral AI behaviour. Yet this paper argues that the solution for AI ethical decision-making resides in algorithm education (as opposed to the training) of ML. Drawing from an analogy between ML and child education for social responsibility, the paper offers clear directions for responsible and sustainable AI design, specifically with respect to how to educate algorithms to decide ethically.

In most conversations about explanation and AI, the recipient of the explanation (the explainee) is suspiciously absent, despite the problem being ultimately communicative in nature. We pose the problem `explaining AI systems' in terms of a two-player cooperative game in which each agent seeks to maximise our proposed measure of explanatory effectiveness. This measure serves as a foundation for the automated assessment of explanations, in terms of the effects that any given action in the game has on the internal state of the explainee.

We present a new model, training procedure and architecture to create precise maps of distinction between two classes of images. The objective is to comprehend, in pixel-wise resolution, the unique characteristics of a class. These maps can facilitate self-supervised segmentation and objectdetection in addition to new capabilities in explainable AI (XAI). Our proposed architecture is based on image decomposition, where the output is the sum of multiple generative networks (branched-GANs). The distinction between classes is isolated in a dedicated branch. This approach allows clear, precise and interpretable visualization of the unique characteristics of each class. We show how our generic method can be used in several modalities for various tasks, such as MRI brain tumor extraction, isolating cars in aerial photography and obtaining feminine and masculine face features. This is a preliminary report of our initial findings and results.

This study aims to relate the time-frequency patterns of acoustic emission (AE) and other multi-modal sensor data collected in a hybrid directed energy deposition (DED) process to the pore formations at high spatial (0.5 mm) and time (< 1ms) resolutions. Adapting an explainable AI method in LIME (Local Interpretable Model-Agnostic Explanations), certain high-frequency waveform signatures of AE are to be attributed to two major pathways for pore formation in a DED process, namely, spatter events and insufficient fusion between adjacent printing tracks from low heat input. This approach opens an exciting possibility to predict, in real-time, the presence of a pore in every voxel (0.5 mm in size) as they are printed, a major leap forward compared to prior efforts. Synchronized multimodal sensor data including force, AE, vibration and temperature were gathered while an SS316L material sample was printed and subsequently machined. A deep convolution neural network classifier was used to identify the presence of pores on a voxel surface based on time-frequency patterns (spectrograms) of the sensor data collected during the process chain. The results suggest signals collected during DED were more sensitive compared to those from machining for detecting porosity in voxels (classification test accuracy of 87%). The underlying explanations drawn from LIME analysis suggests that energy captured in high frequency AE waveforms are 33% lower for porous voxels indicating a relatively lower laser-material interaction in the melt pool, and hence insufficient fusion and poor overlap between adjacent printing tracks. The porous voxels for which spatter events were prevalent during printing had about 27% higher energy contents in the high frequency AE band compared to other porous voxels. These signatures from AE signal can further the understanding of pore formation from spatter and insufficient fusion.

This workshop Report Out focuses on the foundational elements of trustworthy AI and OR technology, and how to ensure all AI and OR systems implement these elements in their system designs. Four sessions on various topics within Trustworthy AI were held, these being Fairness, Explainable AI/Causality, Robustness/Privacy, and Human Alignment and Human-Computer Interaction. Following discussions of each of these topics, workshop participants also brainstormed challenge problems which require the collaboration of AI and OR researchers and will result in the integration of basic techniques from both fields to eventually benefit societal needs.

Is the rapid adoption of Artificial Intelligence a sign that creative destruction (a capitalist innovation process first theorised in 1942) is occurring? Although its theory suggests that it is only visible over time in aggregate, this paper devises three hypotheses to test its presence on a macro level and research methods to produce the required data. This paper tests the theory using news archives, questionnaires, and interviews with industry professionals. It considers the risks of adopting Artificial Intelligence, its current performance in the market and its general applicability to the role. The results suggest that creative destruction is occurring in the AML industry despite the activities of the regulators acting as natural blockers to innovation. This is a pressurised situation where current-generation Artificial Intelligence may offer more harm than benefit. For managers, this papers results suggest that safely pursuing AI in AML requires having realistic expectations of Artificial Intelligence's benefits combined with using a framework for AI Ethics.

Several explainable AI methods allow a Machine Learning user to get insights on the classification process of a black-box model in the form of local linear explanations. With such information, the user can judge which features are locally relevant for the classification outcome, and get an understanding of how the model reasons. Standard supervised learning processes are purely driven by the original features and target labels, without any feedback loop informed by the local relevance of the features identified by the post-hoc explanations. In this paper, we exploit this newly obtained information to design a feature engineering phase, where we combine explanations with feature values. To do so, we develop two different strategies, named Iterative Dataset Weighting and Targeted Replacement Values, which generate streamlined models that better mimic the explanation process presented to the user. We show how these streamlined models compare to the original black-box classifiers, in terms of accuracy and compactness of the newly produced explanations.

Two fundamental requirements for the deployment of machine learning models in safety-critical systems are to be able to detect out-of-distribution (OOD) data correctly and to be able to explain the prediction of the model. Although significant effort has gone into both OOD detection and explainable AI, there has been little work on explaining why a model predicts a certain data point is OOD. In this paper, we address this question by introducing the concept of an OOD counterfactual, which is a perturbed data point that iteratively moves between different OOD categories. We propose a method for generating such counterfactuals, investigate its application on synthetic and benchmark data, and compare it to several benchmark methods using a range of metrics.

This paper proposes an alternative approach to the basic taxonomy of explanations produced by explainable artificial intelligence techniques. Methods of Explainable Artificial Intelligence (XAI) were developed to answer the question why a certain prediction or estimation was made, preferably in terms easy to understand by the human agent. XAI taxonomies proposed in the literature mainly concentrate their attention on distinguishing explanations with respect to involving the human agent, which makes it complicated to provide a more mathematical approach to distinguish and compare different explanations. This paper narrows its attention to the cases where the data set of interest belongs to $\mathbb{R} ^n$ and proposes a simple linear algebra-based taxonomy for local explanations.

The scalability of modern computing hardware is limited by physical bottlenecks and high energy consumption. These limitations could be addressed by neuromorphic hardware (NMH) which is inspired by the human brain. NMH enables physically built-in capabilities of information processing at the hardware level. In other words, brain-like features bias hardware towards intelligence at scale. Neuropmorphic computing paradigms require a novel approach to safe, interpretable AI. In order to effectively engage the risk of misaligned AI, safety research may need to expand its scope to include NMH. This may be best achieved by supporting those currently engaged in NMH capability research to work on safety and related areas.