This paper describes the Ubenwa CryCeleb dataset - a labeled collection of infant cries - and the accompanying CryCeleb 2023 task, which is a public speaker verification challenge based on cry sounds. We released more than 6 hours of manually segmented cry sounds from 786 newborns for academic use, aiming to encourage research in infant cry analysis. The inaugural public competition attracted 59 participants, 11 of whom improved the baseline performance. The top-performing system achieved a significant improvement scoring 25.8% equal error rate, which is still far from the performance of state-of-the-art adult speaker verification systems. Therefore, we believe there is room for further research on this dataset, potentially extending beyond the verification task.

This enables immediate control over vehicle functions like brakes, acceleration, and steering. It offers advantages such as contributing to traffic safety by delivering precise information directly to drivers. However, the dynamic nature of VANETs, marked by constantly changing network topologies, varying vehicle speeds, and differences in the density of V2X communications, introduces new challenges and vulnerabilities that must be addressed [1]. These vulnerabilities can be exploited to launch various types of attacks, which could result in various issues such as accidents and traffic congestion. Thus, ensuring the security of VANETs is of great significance due to the potential risks to human lives, property, and economic activities. This underscores the need to prioritize the development of robust information system security tools and mechanisms capable of not only detecting but also effectively mitigating these attacks. Taking proactive measures is essential to ensure the integrity and safety of VANETs in the face of the evolving cybersecurity threats.

We study the implications of the modeling choice to use a graph, instead of a hypergraph, to represent real-world interconnected systems whose constituent relationships are of higher order by nature. Such a modeling choice typically involves an underlying projection process that maps the original hypergraph onto a graph, and is common in graph-based analysis. While hypergraph projection can potentially lead to loss of higher-order relations, there exists very limited studies on the consequences of doing so, as well as its remediation. This work fills this gap by doing two things: (1) we develop analysis based on graph and set theory, showing two ubiquitous patterns of hyperedges that are root to structural information loss in all hypergraph projections; we also quantify the combinatorial impossibility of recovering the lost higher-order structures if no extra help is provided; (2) we still seek to recover the lost higher-order structures in hypergraph projection, and in light of (1)'s findings we propose to relax the problem into a learning-based setting. Under this setting, we develop a learning-based hypergraph reconstruction method based on an important statistic of hyperedge distributions that we find. Our reconstruction method is evaluated on 8 real-world datasets under different settings, and exhibits consistently good performance. We also demonstrate benefits of the reconstructed hypergraphs via use cases of protein rankings and link predictions.

The advent of Federated Learning has enabled the creation of a high-performing model as if it had been trained on a considerable amount of data. A multitude of participants and a server cooperatively train a model without the need for data disclosure or collection. The healthcare industry, where security and privacy are paramount, can substantially benefit from this new learning paradigm, as data collection is no longer feasible due to stringent data policies. Nonetheless, unaddressed challenges and insufficient attack mitigation are hampering its adoption. Attack surfaces differ from traditional centralized learning in that the server and clients communicate between each round of training. In this paper, we thus present vulnerabilities, attacks, and defenses based on the widened attack surfaces, as well as suggest promising new research directions toward a more robust FL.

Sparse principal component analysis (PCA) aims at mapping large dimensional data to a linear subspace of lower dimension. By imposing loading vectors to be sparse, it performs the double duty of dimension reduction and variable selection. Sparse PCA algorithms are usually expressed as a trade-off between explained variance and sparsity of the loading vectors (i.e., number of selected variables). As a high explained variance is not necessarily synonymous with relevant information, these methods are prone to select irrelevant variables. To overcome this issue, we propose an alternative formulation of sparse PCA driven by the false discovery rate (FDR). We then leverage the Terminating-Random Experiments (T-Rex) selector to automatically determine an FDR-controlled support of the loading vectors. A major advantage of the resulting T-Rex PCA is that no sparsity parameter tuning is required. Numerical experiments and a stock market data example demonstrate a significant performance improvement.

Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications. In spite of these successes, there exist concerns that limit the wide application of LLMs. A key problem is the problem of hallucination. Hallucination refers to the fact that in addition to correct responses, LLMs can also generate seemingly correct but factually incorrect responses. This report aims to present a comprehensive review of the current literature on both hallucination detection and hallucination mitigation. We hope that this report can serve as a good reference for both engineers and researchers who are interested in LLMs and applying them to real world tasks.

The performance of machine learning models often degrades after deployment due to data distribution shifts. In many use cases, it is impossible to calculate the post-deployment performance because labels are unavailable or significantly delayed. Proxy methods for evaluating model performance stability, like drift detection techniques, do not properly quantify data distribution shift impact. As a solution, we propose a robust and accurate performance estimation method for evaluating ML classification models on unlabeled data that accurately quantifies the impact of covariate shift on model performance. We call it multi-calibrated confidence-based performance estimation (M-CBPE). It is model and data-type agnostic and works for any performance metric. It does not require access to the monitored model - it uses the model predictions and probability estimates. M-CBPE does not need user input on the nature of the covariate shift as it fully learns from the data. We evaluate it with over 600 dataset-model pairs from US census data and compare it with multiple benchmarks using several evaluation metrics. Results show that M-CBPE is the best method to estimate the performance of classification models in any evaluation context.

With the rapid growth of Vehicle Ad-hoc Network (VANET) as a promising technology for efficient and reliable communication among vehicles and infrastructure, the security and integrity of VANET communications has become a critical concern. One of the significant threats to VANET is the presence of blackhole attacks, where malicious nodes disrupt the network's functionality and compromise data confidentiality, integrity, and availability. In this paper, we propose a machine learning-based approach for blackhole detection in VANET. To achieve this task, we first create a comprehensive dataset comprising normal and malicious traffic flows. Afterward, we study and define a promising set of features to discriminate the blackhole attacks. Finally, we evaluate various machine learning algorithms, including Gradient Boosting, Random Forest, Support Vector Machines, k-Nearest Neighbors, Gaussian Naive Bayes, and Logistic Regression. Experimental results demonstrate the effectiveness of these algorithms in distinguishing between normal and malicious nodes. Our findings also highlight the potential of machine learning based approach in enhancing the security of VANET by detecting and mitigating blackhole attacks.

Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world settings. In this paper, we offer an innovative perspective on quantifying the disparities between in-distribution (ID) and OOD data -- analyzing the uncertainty that arises when models attempt to explain their predictive decisions. This perspective is motivated by our observation that gradient-based attribution methods encounter challenges in assigning feature importance to OOD data, thereby yielding divergent explanation patterns. Consequently, we investigate how attribution gradients lead to uncertain explanation outcomes and introduce two forms of abnormalities for OOD detection: the zero-deflation abnormality and the channel-wise average abnormality. We then propose GAIA, a simple and effective approach that incorporates Gradient Abnormality Inspection and Aggregation. The effectiveness of GAIA is validated on both commonly utilized (CIFAR) and large-scale (ImageNet-1k) benchmarks. Specifically, GAIA reduces the average FPR95 by 23.10% on CIFAR10 and by 45.41% on CIFAR100 compared to advanced post-hoc methods.

Boulders form from a variety of geological processes, which their size, shape, and orientation may help us better understand. Furthermore, they represent potential hazards to spacecraft landing that need to be characterized. However, mapping individual boulders across vast areas is extremely labor-intensive, often limiting the extent over which they are characterized and the statistical robustness of obtained boulder morphometrics. To automate boulder characterization, we use an instance segmentation neural network, Mask R-CNN, to detect and outline boulders in high-resolution satellite images. Our neural network, BoulderNet, was trained from a dataset of > 33,000 boulders in > 750 image tiles from Earth, the Moon, and Mars. BoulderNet not only correctly detects the majority of boulders in images, but it identifies the outline of boulders with high fidelity, achieving average precision and recall values of 72% and 64% relative to manually digitized boulders from the test dataset, when only detections with intersection-over-union ratios > 50% are considered valid. These values are similar to those obtained by human mappers. On Earth, equivalent boulder diameters, aspect ratios, and orientations extracted from predictions were benchmarked against ground measurements and yield values within 15%, 0.20, and 20 degrees of their ground-truth values, respectively. BoulderNet achieves better boulder detection and characterization performance relative to existing methods, providing a versatile open-source tool to characterize entire boulder fields on planetary surfaces.