Recent work suggests that large language models (LLMs) can improve performance of speech tasks compared to existing systems. To support their claims, results on LibriSpeech and Common Voice are often quoted. However, this work finds that a substantial amount of the LibriSpeech and Common Voice evaluation sets appear in public LLM pretraining corpora. This calls into question the reliability of findings drawn from these two datasets. To measure contamination impact, LLMs trained with/without contamination are compared. A contaminated LLM is more likely to generate test sentences it has seen during training. Then, speech recognisers based on LLMs are compared. They show only subtle error rate differences if the LLM is contaminated, but assign significantly higher probabilities to transcriptions seen during LLM training. Results show that LLM outputs can be biased by tiny amounts of data contamination, highlighting the importance of evaluating LLM-based speech systems with held-out data.

Social media platforms have experienced a significant rise in toxic content, including abusive language and discriminatory remarks, presenting growing challenges for content moderation. Some users evade censorship by deliberately disguising toxic words through homophonic cloak, which necessitates the task of unveiling cloaked toxicity. Existing methods are mostly designed for English texts, while Chinese cloaked toxicity unveiling has not been solved yet. To tackle the issue, we propose C$^2$TU, a novel training-free and prompt-free method for Chinese cloaked toxic content unveiling. It first employs substring matching to identify candidate toxic words based on Chinese homo-graph and toxic lexicon. Then it filters those candidates that are non-toxic and corrects cloaks to be their corresponding toxicities. Specifically, we develop two model variants for filtering, which are based on BERT and LLMs, respectively. For LLMs, we address the auto-regressive limitation in computing word occurrence probability and utilize the full semantic contexts of a text sequence to reveal cloaked toxic words. Extensive experiments demonstrate that C$^2$TU can achieve superior performance on two Chinese toxic datasets. In particular, our method outperforms the best competitor by up to 71% on the F1 score and 35% on accuracy, respectively. Our code and data are available at https://github.com/XDxc-cuber/C2TU-Chinese-cloaked-toxicity-unveiling.

Purpose: Automated Surgical Phase Recognition (SPR) uses Artificial Intelligence (AI) to segment the surgical workflow into its key events, functioning as a building block for efficient video review, surgical education as well as skill assessment. Previous research has focused on short and linear surgical procedures and has not explored if temporal context influences experts' ability to better classify surgical phases. This research addresses these gaps, focusing on Robot-Assisted Partial Nephrectomy (RAPN) as a highly non-linear procedure. Methods: Urologists of varying expertise were grouped and tasked to indicate the surgical phase for RAPN on both single frames and video snippets using a custom-made web platform. Participants reported their confidence levels and the visual landmarks used in their decision-making. AI architectures without and with temporal context as trained and benchmarked on the Cholec80 dataset were subsequently trained on this RAPN dataset. Results: Video snippets and presence of specific visual landmarks improved phase classification accuracy across all groups. Surgeons displayed high confidence in their classifications and outperformed novices, who struggled discriminating phases. The performance of the AI models is comparable to the surgeons in the survey, with improvements when temporal context was incorporated in both cases. Conclusion: SPR is an inherently complex task for expert surgeons and computer vision, where both perform equally well when given the same context. Performance increases when temporal information is provided. Surgical tools and organs form the key landmarks for human interpretation and are expected to shape the future of automated SPR.

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are insufficient to audit the resulting risks. We hypothesize that those tools' shortcomings are due to mismatched assumptions. Thus, we argue that effectively measuring privacy leakage in sequence models requires leveraging the correlations inherent in sequential generation. To illustrate this, we adapt a state-of-the-art membership inference attack to explicitly model within-sequence correlations, thereby demonstrating how a strong existing attack can be naturally extended to suit the structure of sequence models. Through a case study, we show that our adaptations consistently improve the effectiveness of memorization audits without introducing additional computational costs. Our work hence serves as an important stepping stone toward reliable memorization audits for large sequence models.

Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain underexplored. To address this gap, we present EMO-Debias, a large-scale comparison of 13 debiasing methods applied to multi-label SER. Our study encompasses techniques from pre-processing, regularization, adversarial learning, biased learners, and distributionally robust optimization. Experiments conducted on acted and naturalistic emotion datasets, using WavLM and XLSR representations, evaluate each method under conditions of gender imbalance. Our analysis quantifies the trade-offs between fairness and accuracy, identifying which approaches consistently reduce gender performance gaps without compromising overall model performance. The findings provide actionable insights for selecting effective debiasing strategies and highlight the impact of dataset distributions.

Energy-based models (EBMs) estimate unnormalized densities in an elegant framework, but they are generally difficult to train. Recent work has linked EBMs to generative adversarial networks, by noting that they can be trained through a minimax game using a variational lower bound. To avoid the instabilities caused by minimizing a lower bound, we propose to instead work with bidirectional bounds, meaning that we maximize a lower bound and minimize an upper bound when training the EBM. We investigate four different bounds on the log-likelihood derived from different perspectives. We derive lower bounds based on the singular values of the generator Jacobian and on mutual information. To upper bound the negative log-likelihood, we consider a gradient penalty-like bound, as well as one based on diffusion processes. In all cases, we provide algorithms for evaluating the bounds. We compare the different bounds to investigate, the pros and cons of the different approaches. Finally, we demonstrate that the use of bidirectional bounds stabilizes EBM training and yields high-quality density estimation and sample generation.

This study investigates the application of machine learning (ML) models for classifying dental providers into two categories - standard rendering providers and safety net clinic (SNC) providers - using a 2018 dataset of 24,300 instances with 20 features. The dataset, characterized by high missing values (38.1%), includes service counts (preventive, treatment, exams), delivery systems (FFS, managed care), and beneficiary demographics. Feature ranking methods such as information gain, Gini index, and ANOVA were employed to identify critical predictors, revealing treatment-related metrics (TXMT_USER_CNT, TXMT_SVC_CNT) as top-ranked features. Twelve ML models, including k-Nearest Neighbors (kNN), Decision Trees, Support Vector Machines (SVM), Stochastic Gradient Descent (SGD), Random Forest, Neural Networks, and Gradient Boosting, were evaluated using 10-fold cross-validation. Classification accuracy was tested across incremental feature subsets derived from rankings. The Neural Network achieved the highest accuracy (94.1%) using all 20 features, followed by Gradient Boosting (93.2%) and Random Forest (93.0%). Models showed improved performance as more features were incorporated, with SGD and ensemble methods demonstrating robustness to missing data. Feature ranking highlighted the dominance of treatment service counts and annotation codes in distinguishing provider types, while demographic variables (AGE_GROUP, CALENDAR_YEAR) had minimal impact. The study underscores the importance of feature selection in enhancing model efficiency and accuracy, particularly in imbalanced healthcare datasets. These findings advocate for integrating feature-ranking techniques with advanced ML algorithms to optimize dental provider classification, enabling targeted resource allocation for underserved populations.

Network Intrusion Detection Systems (NIDS) play a vital role in protecting digital infrastructures against increasingly sophisticated cyber threats. In this paper, we extend ODXU, a Neurosymbolic AI (NSAI) framework that integrates deep embedded clustering for feature extraction, symbolic reasoning using XGBoost, and comprehensive uncertainty quantification (UQ) to enhance robustness, interpretability, and generalization in NIDS. The extended ODXU incorporates score-based methods (e.g., Confidence Scoring, Shannon Entropy) and metamodel-based techniques, including SHAP values and Information Gain, to assess the reliability of predictions. Experimental results on the CIC-IDS-2017 dataset show that ODXU outperforms traditional neural models across six evaluation metrics, including classification accuracy and false omission rate. While transfer learning has seen widespread adoption in fields such as computer vision and natural language processing, its potential in cybersecurity has not been thoroughly explored. To bridge this gap, we develop a transfer learning strategy that enables the reuse of a pre-trained ODXU model on a different dataset. Our ablation study on ACI-IoT-2023 demonstrates that the optimal transfer configuration involves reusing the pre-trained autoencoder, retraining the clustering module, and fine-tuning the XGBoost classifier, and outperforms traditional neural models when trained with as few as 16,000 samples (approximately 50% of the training data). Additionally, results show that metamodel-based UQ methods consistently outperform score-based approaches on both datasets.

In recent years, quantum machine learning has emerged as a promising intersection between quantum physics and artificial intelligence, particularly in domains requiring advanced pattern recognition such as healthcare. This study investigates the effectiveness of Quantum Support Vector Machines (QSVM), which leverage quantum mechanical phenomena like superposition and entanglement to construct high-dimensional Hilbert spaces for data classification. Focusing on lung cancer diagnosis, a concrete and critical healthcare application, we analyze how different quantum feature maps influence classification performance. Using a real-world dataset of 309 patient records with significant class imbalance (39 non-cancer vs. 270 cancer cases), we constructed six balanced subsets for robust evaluation. QSVM models were implemented using Qiskit and executed on the qasm simulator, employing three distinct quantum feature maps: ZFeatureMap, ZZFeatureMap, and PauliFeatureMap. Performance was assessed using accuracy, precision, recall, specificity, and F1-score. Results show that the PauliFeatureMap consistently outperformed the others, achieving perfect classification in three subsets and strong performance overall. These findings demonstrate how quantum computational principles can be harnessed to enhance diagnostic capabilities, reinforcing the importance of physics-based modeling in emerging AI applications within healthcare.

The Bayes Error Rate (BER) is the fundamental limit on the achievable generalizable classification accuracy of any machine learning model due to inherent uncertainty within the data. BER estimators offer insight into the difficulty of any classification problem and set expectations for optimal classification performance. In order to be useful, the estimators must also be accurate with a limited number of samples on multivariate problems with unknown class distributions. To determine which estimators meet the minimum requirements for "usefulness", an in-depth examination of their accuracy is conducted using Monte Carlo simulations with synthetic data in order to obtain their confidence bounds for binary classification. To examine the usability of the estimators on real-world applications, new test scenarios are introduced upon which 2500 Monte Carlo simulations per scenario are run over a wide range of BER values. In a comparison of k-Nearest Neighbor (kNN), Generalized Henze-Penrose (GHP) divergence and Kernel Density Estimation (KDE) techniques, results show that kNN is overwhelmingly the more accurate non-parametric estimator. In order to reach the target of an under 5 percent range for the 95 percent confidence bounds, the minimum number of required samples per class is 1000. As more features are added, more samples are needed, so that 2500 samples per class are required at only 4 features. Other estimators do become more accurate than kNN as more features are added, but continuously fail to meet the target range.