The emergence of a variety of Machine Learning (ML) approaches for travel mode choice prediction poses an interesting question to transport modellers: which models should be used for which applications? The answer to this question goes beyond simple predictive performance, and is instead a balance of many factors, including behavioural interpretability and explainability, computational complexity, and data efficiency. There is a growing body of research which attempts to compare the predictive performance of different ML classifiers with classical random utility models. However, existing studies typically analyse only the disaggregate predictive performance, ignoring other aspects affecting model choice. Furthermore, many studies are affected by technical limitations, such as the use of inappropriate validation schemes, incorrect sampling for hierarchical data, lack of external validation, and the exclusive use of discrete metrics. We address these limitations by conducting a systematic comparison of different modelling approaches, across multiple modelling problems, in terms of the key factors likely to affect model choice (out-of-sample predictive performance, accuracy of predicted market shares, extraction of behavioural indicators, and computational efficiency). We combine several real world datasets with synthetic datasets, where the data generation function is known. The results indicate that the models with the highest disaggregate predictive performance (namely extreme gradient boosting and random forests) provide poorer estimates of behavioural indicators and aggregate mode shares, and are more expensive to estimate, than other models, including deep neural networks and Multinomial Logit (MNL). It is further observed that the MNL model performs robustly in a variety of situations, though ML techniques can improve the estimates of behavioural indices such as Willingness to Pay.

Matching algorithms are commonly used to predict matches between items in a collection. For example, in 1:1 face verification, a matching algorithm predicts whether two face images depict the same person. Accurately assessing the uncertainty of the error rates of such algorithms can be challenging when data are dependent and error rates are low, two aspects that have been often overlooked in the literature. In this work, we review methods for constructing confidence intervals for error rates in 1:1 matching tasks. We derive and examine the statistical properties of these methods, demonstrating how coverage and interval width vary with sample size, error rates, and degree of data dependence on both analysis and experiments with synthetic and real-world datasets. Based on our findings, we provide recommendations for best practices for constructing confidence intervals for error rates in 1:1 matching tasks.

As robots acquire increasingly sophisticated skills and see increasingly complex and varied environments, the threat of an edge case or anomalous failure is ever present. For example, Tesla cars have seen interesting failure modes ranging from autopilot disengagements due to inactive traffic lights carried by trucks to phantom braking caused by images of stop signs on roadside billboards. These system-level failures are not due to failures of any individual component of the autonomy stack but rather system-level deficiencies in semantic reasoning. Such edge cases, which we call semantic anomalies, are simple for a human to disentangle yet require insightful reasoning. To this end, we study the application of large language models (LLMs), endowed with broad contextual understanding and reasoning capabilities, to recognize such edge cases and introduce a monitoring framework for semantic anomaly detection in vision-based policies. Our experiments apply this framework to a finite state machine policy for autonomous driving and a learned policy for object manipulation. These experiments demonstrate that the LLM-based monitor can effectively identify semantic anomalies in a manner that shows agreement with human reasoning. Finally, we provide an extended discussion on the strengths and weaknesses of this approach and motivate a research outlook on how we can further use foundation models for semantic anomaly detection.

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum, when in reality, ML models are part of larger systems that include components for training data filtering, output monitoring, and more. In this work, we introduce privacy side channels: attacks that exploit these system-level components to extract private information at far higher rates than is otherwise possible for standalone models. We propose four categories of side channels that span the entire ML lifecycle (training data filtering, input preprocessing, output post-processing, and query filtering) and allow for either enhanced membership inference attacks or even novel threats such as extracting users' test queries. For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees. Moreover, we show that systems which block language models from regenerating training data can be exploited to allow exact reconstruction of private keys contained in the training set -- even if the model did not memorize these keys. Taken together, our results demonstrate the need for a holistic, end-to-end privacy analysis of machine learning.

The last decades have seen a growth in the number of cyber-attacks with severe economic and privacy damages, which reveals the need for network intrusion detection approaches to assist in preventing cyber-attacks and reducing their risks. In this work, we propose a novel network representation as a graph of flows that aims to provide relevant topological information for the intrusion detection task, such as malicious behavior patterns, the relation between phases of multi-step attacks, and the relation between spoofed and pre-spoofed attackers activities. In addition, we present a Graph Neural Network (GNN) based framework responsible for exploiting the proposed graph structure to classify communication flows by assigning them a maliciousness score. The framework comprises three main steps that aim to embed nodes features and learn relevant attack patterns from the network representation. Finally, we highlight a potential data leakage issue with classical evaluation procedures and suggest a solution to ensure a reliable validation of intrusion detection systems performance. We implement the proposed framework and prove that exploiting the flow-based graph structure outperforms the classical machine learning-based and the previous GNN-based solutions.

The notion of individual fairness is a formalization of an ethical principle, "Treating like cases alike," which has been argued such as by Aristotle. In a fairness-aware machine learning context, Dwork et al. firstly formalized the notion. In their formalization, a similar pair of data in an unfair space should be mapped to similar positions in a fair space. We propose to re-formalize individual fairness by the statistical independence conditioned by individuals. This re-formalization has the following merits. First, our formalization is compatible with that of Dwork et al. Second, our formalization enables to combine individual fairness with the fairness notion, equalized odds or sufficiency, as well as statistical parity. Third, though their formalization implicitly assumes a pre-process approach for making fair prediction, our formalization is applicable to an in-process or post-process approach.

Peer review is the method employed by the scientific community for evaluating research advancements. In the field of cybersecurity, the practice of double-blind peer review is the de-facto standard. This paper touches on the holy grail of peer reviewing and aims to shed light on the performance of AI in reviewing for academic security conferences. Specifically, we investigate the predictability of reviewing outcomes by comparing the results obtained from human reviewers and machine-learning models. To facilitate our study, we construct a comprehensive dataset by collecting thousands of papers from renowned computer science conferences and the arXiv preprint website. Based on the collected data, we evaluate the prediction capabilities of ChatGPT and a two-stage classification approach based on the Doc2Vec model with various classifiers. Our experimental evaluation of review outcome prediction using the Doc2Vec-based approach performs significantly better than the ChatGPT and achieves an accuracy of over 90%. While analyzing the experimental results, we identify the potential advantages and limitations of the tested ML models. We explore areas within the paper-reviewing process that can benefit from automated support approaches, while also recognizing the irreplaceable role of human intellect in certain aspects that cannot be matched by state-of-the-art AI techniques.

Link prediction is a key aspect of graph machine learning, with applications as diverse as disease prediction, social network recommendations, and drug discovery. It involves predicting new links that may form between network nodes. Despite the clear importance of link prediction, existing models have significant shortcomings. Graph Convolutional Networks, for instance, have been proven to be highly efficient for link prediction on a variety of datasets. However, they encounter severe limitations when applied to short-path networks and ego networks, resulting in poor performance. This presents a critical problem space that this work aims to address. In this paper, we present the Node Centrality and Similarity Based Parameterised Model (NCSM), a novel method for link prediction tasks. NCSM uniquely integrates node centrality and similarity measures as edge features in a customised Graph Neural Network (GNN) layer, effectively leveraging the topological information of large networks. This model represents the first parameterised GNN-based link prediction model that considers topological information. The proposed model was evaluated on five benchmark graph datasets, each comprising thousands of nodes and edges. Experimental results highlight NCSM's superiority over existing state-of-the-art models like Graph Convolutional Networks and Variational Graph Autoencoder, as it outperforms them across various metrics and datasets. This exceptional performance can be attributed to NCSM's innovative integration of node centrality, similarity measures, and its efficient use of topological information.

ABSTRACT -- Exploring methods and techniques of machine learning (ML) to address specific challenges in various fields is essential. In this work, we tackle a problem in the domain of Cheminformatics; that is, providing a suitable solution to aid in predicting the activity of a chemical compound to the best extent possible. To address the problem at hand, this study conducts experiments on 100 different combinations of existing techniques. These solutions are then selected based on a set of criteria that includes the G-means, F1-score, and AUC metrics. The results have been tested on a dataset of about 10,000 chemical compounds from PubChem that have been classified according to their activity. I. INTRODUCTION In datasets used in biological experiments for measuring the activity of various compounds against different biological targets, often used in screening, there is usually a significant imbalance between active and inactive compounds, with the number of inactive data points being much larger. Therefore, training requires the use of suitable machine learning models. Additionally, preprocessing before using machine learning methods for training is also a crucial issue. The following issues are approached to address the problem of predicting the activity of chemical compounds using chemistry-related datasets: Investigating the dependency of attributes or features in the dataset to potentially reduce the number of features. This can be done using methods such as ANOVA F-test to assess the dependency of each feature on the target variable or by using correlation coefficients.

The development of large high-quality datasets and high-performing models have led to significant advancements in the domain of Extractive Question Answering (EQA). This progress has sparked considerable interest in exploring unanswerable questions within the EQA domain. Training EQA models with unanswerable questions helps them avoid extracting misleading or incorrect answers for queries that lack valid responses. However, manually annotating unanswerable questions is labor-intensive. To address this, we propose AGent, a novel pipeline that automatically creates new unanswerable questions by re-matching a question with a context that lacks the necessary information for a correct answer. In this paper, we demonstrate the usefulness of this AGent pipeline by creating two sets of unanswerable questions from answerable questions in SQuAD and HotpotQA. These created question sets exhibit low error rates. Additionally, models fine-tuned on these questions show comparable performance with those fine-tuned on the SQuAD 2.0 dataset on multiple EQA benchmarks.