The ability to detect macroscopic changes is important for probing the behaviors of experimental many-body systems from the classical to the quantum realm. Although abrupt changes near phase boundaries can easily be detected, subtle macroscopic changes are much more difficult to detect as the changes can be obscured by noise. In this study, as a toy model for detecting subtle macroscopic changes in many-body systems, we try to differentiate scalar field samples at varying temperatures. We compare different methods for making such differentiations, from physics method, statistics method, to AI method. Our finding suggests that the AI method outperforms both the statistical method and the physics method in its sensitivity. Our result provides a proof-of-concept that AI can potentially detect macroscopic changes in many-body systems that elude physical measures.

Sentiment analysis of social media data is an emerging field with vast applications in various domains. In this study, we developed a sentiment analysis model to analyze social media sentiment, especially tweets, during global conflicting scenarios. To establish our research experiment, we identified a recent global dispute incident on Twitter and collected around 31,000 filtered Tweets for several months to analyze human sentiment worldwide.

The overarching objective of this paper is two-fold. First, to explore model-based approaches to characterize the primary cause of the noise. in the RE dataset TACRED Second, to identify the potentially noisy instances. Towards the first objective, we analyze predictions and performance of state-of-the-art (SOTA) models to identify the root cause of noise in the dataset. Our analysis of TACRED shows that the majority of the noise in the dataset originates from the instances labeled as no-relation which are negative examples. For the second objective, we explore two nearest-neighbor-based strategies to automatically identify potentially noisy examples for elimination and reannotation. Our first strategy, referred to as Intrinsic Strategy (IS), is based on the assumption that positive examples are clean. Thus, we have used false-negative predictions to identify noisy negative examples. Whereas, our second approach, referred to as Extrinsic Strategy, is based on using a clean subset of the dataset to identify potentially noisy negative examples. Finally, we retrained the SOTA models on the eliminated and reannotated dataset. Our empirical results based on two SOTA models trained on TACRED-E following the IS show an average 4% F1-score improvement, whereas reannotation (TACRED-R) does not improve the original results. However, following ES, SOTA models show the average F1-score improvement of 3.8% and 4.4% when trained on respective eliminated (TACRED-EN) and reannotated (TACRED-RN) datasets respectively. We further extended the ES for cleaning positive examples as well, which resulted in an average performance improvement of 5.8% and 5.6% for the eliminated (TACRED-ENP) and reannotated (TACRED-RNP) datasets respectively.

Vision-language models (VLMs) offer a promising paradigm for image classification by comparing the similarity between images and class embeddings. A critical challenge lies in crafting precise textual representations for class names. While previous studies have leveraged recent advancements in large language models (LLMs) to enhance these descriptors, their outputs often suffer from ambiguity and inaccuracy. We identify two primary causes: 1) The prevalent reliance on textual interactions with LLMs, leading to a mismatch between the generated text and the visual content in VLMs' latent space - a phenomenon we term the "explain without seeing" dilemma. 2) The oversight of the inter-class relationships, resulting in descriptors that fail to differentiate similar classes effectively. To address these issues, we propose a novel image classification framework combining VLMs with LLMs, named Iterative Optimization with Visual Feedback. In particular, our method develops an LLM-based agent, employing an evolutionary optimization strategy to refine class descriptors. Crucially, we incorporate visual feedback from VLM classification metrics, thereby guiding the optimization process with concrete visual data. Our method leads to improving accuracy on a wide range of image classification benchmarks, with 3.47\% average gains over state-of-the-art methods. We also highlight the resulting descriptions serve as explainable and robust features that can consistently improve the performance across various backbone models.

Human Assumed Central Sensitization is involved in the development and maintenance of chronic low back pain (CLBP). The Central Sensitization Inventory (CSI) was developed to evaluate the presence of HACS, with a cut-off value of 40/100 based on patients with chronic pain. However, various factors including pain conditions (e.g., CLBP), and gender may influence this cut-off value. For chronic pain condition such as CLBP, unsupervised clustering approaches can take these factors into consideration and automatically learn the HACS-related patterns. Therefore, this study aimed to determine the cut-off values for a Dutch-speaking population with CLBP, considering the total group and stratified by gender based on unsupervised machine learning. In this study, questionnaire data covering pain, physical, and psychological aspects were collected from patients with CLBP and aged-matched pain-free adults (referred to as healthy controls, HC). Four clustering approaches were applied to identify HACS-related clusters based on the questionnaire data and gender. The clustering performance was assessed using internal and external indicators. Subsequently, receiver operating characteristic analysis was conducted on the best clustering results to determine the optimal cut-off values. The study included 151 subjects, consisting of 63 HCs and 88 patients with CLBP. Hierarchical clustering yielded the best results, identifying three clusters: healthy group, CLBP with low HACS level, and CLBP with high HACS level groups. Based on the low HACS levels group (including HC and CLBP with low HACS level) and high HACS level group, the cut-off value for the overall groups were 35, 34 for females, and 35 for. The findings suggest that the optimal cut-off values for CLBP is 35. The gender-related cut-off values should be interpreted with caution due to the unbalanced gender distribution in the sample.

Artificial Intelligence (AI) systems such as autonomous vehicles, facial recognition, and speech recognition systems are increasingly integrated into our daily lives. However, despite their utility, these AI systems are vulnerable to a wide range of attacks such as adversarial, backdoor, data poisoning, membership inference, model inversion, and model stealing attacks. In particular, numerous attacks are designed to target a particular model or system, yet their effects can spread to additional targets, referred to as transferable attacks. Although considerable efforts have been directed toward developing transferable attacks, a holistic understanding of the advancements in transferable attacks remains elusive. In this paper, we comprehensively explore learning-based attacks from the perspective of transferability, particularly within the context of cyber-physical security. We delve into different domains -- the image, text, graph, audio, and video domains -- to highlight the ubiquitous and pervasive nature of transferable attacks. This paper categorizes and reviews the architecture of existing attacks from various viewpoints: data, process, model, and system. We further examine the implications of transferable attacks in practical scenarios such as autonomous driving, speech recognition, and large language models (LLMs). Additionally, we outline the potential research directions to encourage efforts in exploring the landscape of transferable attacks. This survey offers a holistic understanding of the prevailing transferable attacks and their impacts across different domains.

Segmenting the boundary between tumor and healthy tissue during surgical cancer resection poses a significant challenge. In recent years, Hyperspectral Imaging (HSI) combined with Machine Learning (ML) has emerged as a promising solution. However, due to the extensive information contained within the spectral domain, most ML approaches primarily classify individual HSI (super-)pixels, or tiles, without taking into account their spatial context. In this paper, we propose an improved methodology that leverages the spatial context of tiles for more robust and smoother segmentation. To address the irregular shapes of tiles, we utilize Graph Neural Networks (GNNs) to propagate context information across neighboring regions. The features for each tile within the graph are extracted using a Convolutional Neural Network (CNN), which is trained simultaneously with the subsequent GNN. Moreover, we incorporate local image quality metrics into the loss function to enhance the training procedure's robustness against low-quality regions in the training images. We demonstrate the superiority of our proposed method using a clinical ex vivo dataset consisting of 51 HSI images from 30 patients. Despite the limited dataset, the GNN-based model significantly outperforms context-agnostic approaches, accurately distinguishing between healthy and tumor tissues, even in images from previously unseen patients. Furthermore, we show that our carefully designed loss function, accounting for local image quality, results in additional improvements. Our findings demonstrate that context-aware GNN algorithms can robustly find tumor demarcations on HSI images, ultimately contributing to better surgery success and patient outcome.

Automated interpretability research has recently attracted attention as a potential research direction that could scale explanations of neural network behavior to large models. Existing automated circuit discovery work applies activation patching to identify subnetworks responsible for solving specific tasks (circuits). In this work, we show that a simple method based on attribution patching outperforms all existing methods while requiring just two forward passes and a backward pass. We apply a linear approximation to activation patching to estimate the importance of each edge in the computational subgraph. Using this approximation, we prune the least important edges of the network. We survey the performance and limitations of this method, finding that averaged over all tasks our method has greater AUC from circuit recovery than other methods.

Bounding privacy leakage over compositions, i.e., privacy accounting, is a key challenge in differential privacy (DP). The privacy parameter ($\eps$ or $\delta$) is often easy to estimate but hard to bound. In this paper, we propose a new differential privacy paradigm called estimate-verify-release (EVR), which addresses the challenges of providing a strict upper bound for privacy parameter in DP compositions by converting an estimate of privacy parameter into a formal guarantee. The EVR paradigm first estimates the privacy parameter of a mechanism, then verifies whether it meets this guarantee, and finally releases the query output based on the verification result. The core component of the EVR is privacy verification. We develop a randomized privacy verifier using Monte Carlo (MC) technique. Furthermore, we propose an MC-based DP accountant that outperforms existing DP accounting techniques in terms of accuracy and efficiency. Our empirical evaluation shows the newly proposed EVR paradigm improves the utility-privacy tradeoff for privacy-preserving machine learning.

The non-life insurance sector operates within a highly competitive and tightly regulated framework, confronting a pivotal juncture in the formulation of pricing strategies. Insurers are compelled to harness a range of statistical methodologies and available data to construct optimal pricing structures that align with the overarching corporate strategy while accommodating the dynamics of market competition. Given the fundamental societal role played by insurance, premium rates are subject to rigorous scrutiny by regulatory authorities. These rates must conform to principles of transparency, explainability, and ethical considerations. Consequently, the act of pricing transcends mere statistical calculations and carries the weight of strategic and societal factors. These multifaceted concerns may drive insurers to establish equitable premiums, taking into account various variables. For instance, regulations mandate the provision of equitable premiums, considering factors such as policyholder gender or mutualist group dynamics in accordance with respective corporate strategies. Age-based premium fairness is also mandated. In certain insurance domains, variables such as the presence of serious illnesses or disabilities are emerging as new dimensions for evaluating fairness. Regardless of the motivating factor prompting an insurer to adopt fairer pricing strategies for a specific variable, the insurer must possess the capability to define, measure, and ultimately mitigate any ethical biases inherent in its pricing practices while upholding standards of consistency and performance. This study seeks to provide a comprehensive set of tools for these endeavors and assess their effectiveness through practical application in the context of automobile insurance.