Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain limited-explored in transfer learning. The interaction between teacher and student models in transfer learning has not been thoroughly explored in MIAs, potentially resulting in an under-examined aspect of privacy vulnerabilities within transfer learning. In this paper, we propose a new MIA vector against transfer learning, to determine whether a specific data point was used to train the teacher model while only accessing the student model in a white-box setting. Our method delves into the intricate relationship between teacher and student models, analyzing the discrepancies in hidden layer representations between the student model and its shadow counterpart. These identified differences are then adeptly utilized to refine the shadow model's training process and to inform membership inference decisions effectively. Our method, evaluated across four datasets in diverse transfer learning tasks, reveals that even when an attacker only has access to the student model, the teacher model's training data remains susceptible to MIAs. We believe our work unveils the unexplored risk of membership inference in transfer learning.

Current explainability methods often produce inconsistent results and struggle to highlight essential signals influencing model inferences. This paper introduces the Evolutionary Independent Deterministic Explanation (EVIDENCE) theory, a novel approach offering a deterministic, model-independent method for extracting significant signals from black-box models. EVIDENCE theory, grounded in robust mathematical formalization, is validated through empirical tests on diverse datasets, including COVID-19 audio diagnostics, Parkinson's disease voice recordings, and the George Tzanetakis music classification dataset (GTZAN). Practical applications of EVIDENCE include improving diagnostic accuracy in healthcare and enhancing audio signal analysis. For instance, in the COVID-19 use case, EVIDENCE-filtered spectrograms fed into a frozen Residual Network with 50 layers (ResNet50) improved precision by 32% for positive cases and increased the Area Under the Curve (AUC) by 16% compared to baseline models. For Parkinson's disease classification, EVIDENCE achieved near-perfect precision and sensitivity, with a macro average F1-Score of 0.997. In the GTZAN, EVIDENCE maintained a high AUC of 0.996, demonstrating its efficacy in filtering relevant features for accurate genre classification. EVIDENCE outperformed other Explainable Artificial Intelligence (XAI) methods such as Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), and Gradient-weighted Class-Activation Mapping (GradCAM) in almost all metrics. These findings indicate that EVIDENCE not only improves classification accuracy but also provides a transparent and reproducible explanation mechanism, crucial for advancing the trustworthiness and applicability of AI systems in real-world settings.

Hydrogen, the most abundant element in the universe, is crucial for understanding galaxy formation and evolution. The 21 cm neutral atomic hydrogen - HI spectral line maps the gas kinematics within galaxies, providing key insights into interactions, galactic structure, and star formation processes. With new radio instruments, the volume and complexity of data is increasing. To analyze and classify integrated HI spectral profiles in a efficient way, this work presents a framework that integrates Machine Learning techniques, combining unsupervised methods and CNNs. To this end, we apply our framework to a selected subsample of 318 spectral HI profiles of the CIG and 30.780 profiles from the Arecibo Legacy Fast ALFA Survey catalogue. Data pre-processing involved the Busyfit package and iterative fitting with polynomial, Gaussian, and double-Lorentzian models. Clustering methods, including K-means, spectral clustering, DBSCAN, and agglomerative clustering, were used for feature extraction and to bootstrap classification we applied K-NN, SVM, and Random Forest classifiers, optimizing accuracy with CNN. Additionally, we introduced a 2D model of the profiles to enhance classification by adding dimensionality to the data. Three 2D models were generated based on transformations and normalised versions to quantify the level of asymmetry. These methods were tested in a previous analytical classification study conducted by the Analysis of the Interstellar Medium in Isolated Galaxies group. This approach enhances classification accuracy and aims to establish a methodology that could be applied to data analysis in future surveys conducted with the Square Kilometre Array (SKA), currently under construction. All materials, code, and models have been made publicly available in an open-access repository, adhering to FAIR principles.

Hallucinations of deep neural models are amongst key challenges in automatic speech recognition (ASR). In this paper, we investigate hallucinations of the Whisper ASR model induced by non-speech audio segments present during inference. By inducting hallucinations with various types of sounds, we show that there exists a set of hallucinations that appear frequently. We then study hallucinations caused by the augmentation of speech with such sounds. Finally, we describe the creation of a bag of hallucinations (BoH) that allows to remove the effect of hallucinations through the post-processing of text transcriptions. The results of our experiments show that such post-processing is capable of reducing word error rate (WER) and acts as a good safeguard against problematic hallucinations.

Bluebottles (\textit{Physalia} spp.) are marine stingers resembling jellyfish, whose presence on Australian beaches poses a significant public risk due to their venomous nature. Understanding the environmental factors driving bluebottles ashore is crucial for mitigating their impact, and machine learning tools are to date relatively unexplored. We use bluebottle marine stinger presence/absence data from beaches in Eastern Sydney, Australia, and compare machine learning models (Multilayer Perceptron, Random Forest, and XGBoost) to identify factors influencing their presence. We address challenges such as class imbalance, class overlap, and unreliable absence data by employing data augmentation techniques, including the Synthetic Minority Oversampling Technique (SMOTE), Random Undersampling, and Synthetic Negative Approach that excludes the negative class. Our results show that SMOTE failed to resolve class overlap, but the presence-focused approach effectively handled imbalance, class overlap, and ambiguous absence data. The data attributes such as the wind direction, which is a circular variable, emerged as a key factor influencing bluebottle presence, confirming previous inference studies. However, in the absence of population dynamics, biological behaviours, and life cycles, the best predictive model appears to be Random Forests combined with Synthetic Negative Approach. This research contributes to mitigating the risks posed by bluebottles to beachgoers and provides insights into handling class overlap and unreliable negative class in environmental modelling.

Class imbalance (CI) is a longstanding problem in machine learning, slowing down training and reducing performances. Although empirical remedies exist, it is often unclear which ones work best and when, due to the lack of an overarching theory. We address a common case of imbalance, that of anomaly (or outlier) detection. We provide a theoretical framework to analyze, interpret and address CI. It is based on an exact solution of the teacher-student perceptron model, through replica theory. Within this framework, one can distinguish several sources of CI: either intrinsic, train or test imbalance. Our analysis reveals that the optimal train imbalance is generally different from 50%, with a non trivial dependence on the intrinsic imbalance, the abundance of data and on the noise in the learning. Moreover, there is a crossover between a small noise training regime where results are independent of the noise level to a high noise regime where performances quickly degrade with noise. Our results challenge some of the conventional wisdom on CI and offer practical guidelines to address it.

Dataset poisoning attacks present a threat against machine learning models because they introduce subtle, ostensibly undetectable changes to the data on which the model will be trained. Moreover, attackers often craft attacks to deterministically change a model's behavior by invoking a latent trigger that they set in the resultant model. We will introduce the precise threat model in which we are interested in Section 2. Researchers often frame dataset poisoning and its analysis from the point of view of optimization theory [1]-[5]. E.g., in the computer vision setting, one might attempt to alter as few pixels as possible in as few images as possible while still producing targeted misclassifications. For text generation, one might aim to change as few tokens as possible to as few corpus sentences as possible while causing targeted semantic misalignment on the next phrase or sentence. In general, this vantage is convenient for conducting attacks. Even locally optimizing the criteria for an attack typically yields a dataset that effectively attacks models trained on it. From this perspective, it is natural to also frame detection of data poisoning as an optimization problem. For example, in [4], it is hypothesized that poisoning a dataset impacts the most dominant features in neural networks trained on it and it is shown that under this assumption poisoning can be provably detected by solving an optimization problem.

Dataset Distillation is the task of synthesizing small datasets from large ones while still retaining comparable predictive accuracy to the original uncompressed dataset. Despite significant empirical progress in recent years, there is little understanding of the theoretical limitations/guarantees of dataset distillation, specifically, what excess risk is achieved by distillation compared to the original dataset, and how large are distilled datasets? In this work, we take a theoretical view on kernel ridge regression (KRR) based methods of dataset distillation such as Kernel Inducing Points. By transforming ridge regression in random Fourier features (RFF) space, we provide the first proof of the existence of small (size) distilled datasets and their corresponding excess risk for shift-invariant kernels. We prove that a small set of instances exists in the original input space such that its solution in the RFF space coincides with the solution of the original data.

The widely observed'benign overfitting phenomenon' in the neural network literature raises the challenge to the bias-variance trade-off' doctrine in the statistical learning theory.Since the generalization ability of the'lazy trained' over-parametrized neural network can be well approximated by that of the neural tangent kernel regression,the curve of the excess risk (namely, the learning curve) of kernel ridge regression attracts increasing attention recently.However, most recent arguments on the learning curve are heuristic and are based on the'Gaussian design' assumption.In this paper, under mild and more realistic assumptions, we rigorously provide a full characterization of the learning curve in the asymptotic senseunder a power-law decay condition of the eigenvalues of the kernel and also the target function.The learning curve elaborates the effect and the interplay of the choice of the regularization parameter, the source condition and the noise.In particular, our results suggest that the'benign overfitting phenomenon' exists in over-parametrized neural networks only when the noise level is small.

When domain knowledge is limited and experimentation is restricted by ethical, financial, or time constraints, practitioners turn to observational causal discovery methods to recover the causal structure, exploiting the statistical properties of their data. Because causal discovery without further assumptions is an ill-posed problem, each algorithm comes with its own set of usually untestable assumptions, some of which are hard to meet in real datasets. Motivated by these considerations, this paper extensively benchmarks the empirical performance of recent causal discovery methods on observational iid data generated under different background conditions, allowing for violations of the critical assumptions required by each selected approach. Our experimental findings show that score matching-based methods demonstrate surprising performance in the false positive and false negative rate of the inferred graph in these challenging scenarios, and we provide theoretical insights into their performance. This work is also the first effort to benchmark the stability of causal discovery algorithms with respect to the values of their hyperparameters.