Search

Although software developers of mHealth apps are responsible for protecting patient data and adhering to strict privacy and security requirements, many of them lack awareness of HIPAA regulations and struggle to distinguish between HIPAA rules categories. Therefore, providing guidance of HIPAA rules patterns classification is essential for developing secured applications for Google Play Store. In this work, we identified the limitations of traditional Word2Vec embeddings in processing code patterns. To address this, we adopt multilingual BERT (Bidirectional Encoder Representations from Transformers) which offers contextualized embeddings to the attributes of dataset to overcome the issues. Therefore, we applied this BERT to our dataset for embedding code patterns and then uses these embedded code to various machine learning approaches. Our results demonstrate that the models significantly enhances classification performance, with Logistic Regression achieving a remarkable accuracy of 99.95\%. Additionally, we obtained high accuracy from Support Vector Machine (99.79\%), Random Forest (99.73\%), and Naive Bayes (95.93\%), outperforming existing approaches. This work underscores the effectiveness and showcases its potential for secure application development.

In this study, we propose a novel and robust framework, Self-DenseMobileNet, designed to enhance the classification of nodules and non-nodules in chest radiographs (CXRs). Our approach integrates advanced image standardization and enhancement techniques to optimize the input quality, thereby improving classification accuracy. To enhance predictive accuracy and leverage the strengths of multiple models, the prediction probabilities from Self-DenseMobileNet were transformed into tabular data and used to train eight classical machine learning (ML) models; the top three performers were then combined via a stacking algorithm, creating a robust meta-classifier that integrates their collective insights for superior classification performance. To enhance the interpretability of our results, we employed class activation mapping (CAM) to visualize the decision-making process of the best-performing model. Our proposed framework demonstrated remarkable performance on internal validation data, achieving an accuracy of 99.28\% using a Meta-Random Forest Classifier. When tested on an external dataset, the framework maintained strong generalizability with an accuracy of 89.40\%. These results highlight a significant improvement in the classification of CXRs with lung nodules., Comment: 31 pages

Exterior painting of high-rise buildings is a challenging task. In our country, as well as in other countries of the world, this task is accomplished manually, which is risky and life-threatening for the workers. Researchers and industry experts are trying to find an automatic and robotic solution for the exterior painting of high-rise building walls. In this paper, we propose a solution to this problem. We design and implement a prototype for automatically painting the building walls' exteriors. A spray mechanism was introduced in the prototype that can move in four different directions (up-down and left-right). All the movements are achieved by using microcontroller-operated servo motors. Further, these components create a scope to upgrade the proposed remote-controlled system to a robotic system in the future. In the presented system, all the operations are controlled remotely from a smartphone interface. Bluetooth technology is used for remote communications. It is expected that the suggested system will improve productivity with better workplace safety.

Countries in South Asia experience many catastrophic flooding events regularly. Through image classification, it is possible to expedite search and rescue initiatives by classifying flood zones, including houses and humans. We create a new dataset collecting aerial imagery of flooding events across South Asian countries. For the classification, we propose a fine-tuned Compact Convolutional Transformer (CCT) based approach and some other cutting-edge transformer-based and Convolutional Neural Network-based architectures (CNN). We also implement the YOLOv8 object detection model and detect houses and humans within the imagery of our proposed dataset, and then compare the performance with our classification-based approach. Since the countries in South Asia have similar topography, housing structure, the color of flood water, and vegetation, this work can be more applicable to such a region as opposed to the rest of the world. The images are divided evenly into four classes: 'flood', 'flood with domicile', 'flood with humans', and 'no flood'. After experimenting with our proposed dataset on our fine-tuned CCT model, which has a comparatively lower number of weight parameters than many other transformer-based architectures designed for computer vision, it exhibits an accuracy and macro average precision of 98.62% and 98.50%. The other transformer-based architectures that we implement are the Vision Transformer (ViT), Swin Transformer, and External Attention Transformer (EANet), which give an accuracy of 88.66%, 84.74%, and 66.56% respectively. We also implement DCECNN (Deep Custom Ensembled Convolutional Neural Network), which is a custom ensemble model that we create by combining MobileNet, InceptionV3, and EfficientNetB0, and we obtain an accuracy of 98.78%. The architectures we implement are fine-tuned to achieve optimal performance on our dataset.

In the digital age, the exposure of sensitive information poses a significant threat to security. Leveraging the ubiquitous nature of code-sharing platforms like GitHub and BitBucket, developers often accidentally disclose credentials and API keys, granting unauthorized access to critical systems. Despite the availability of tools for detecting such breaches in source code, detecting secret breaches in software issue reports remains largely unexplored. This paper presents a novel technique for secret breach detection in software issue reports using a combination of language models and state-of-the-art regular expressions. We highlight the challenges posed by noise, such as log files, URLs, commit IDs, stack traces, and dummy passwords, which complicate the detection process. By employing relevant pre-processing techniques and leveraging the capabilities of advanced language models, we aim to mitigate potential breaches effectively. Drawing insights from existing research on secret detection tools and methodologies, we propose an approach combining the strengths of state-of-the-art regexes with the contextual understanding of language models. Our method aims to reduce false positives and improve the accuracy of secret breach detection in software issue reports. We have curated a benchmark dataset of 25000 instances with only 437 true positives. Although the data is highly skewed, our model performs well with a 0.6347 F1-score, whereas state-of-the-art regular expression hardly manages to get a 0.0341 F1-Score with a poor precision score. We have also developed a secret breach mitigator tool for GitHub, which will warn the user if there is any secret in the posted issue report. By addressing this critical gap in contemporary research, our work aims at enhancing the overall security posture of software development practices., Comment: Under review in ACM Transactions on Software Engineering and Methodology (TOSEM)

The growing volume of biomedical scholarly document abstracts presents an increasing challenge in efficiently retrieving accurate and relevant information. To address this, we introduce a novel approach that integrates an optimized topic modelling framework, OVB-LDA, with the BI-POP CMA-ES optimization technique for enhanced scholarly document abstract categorization. Complementing this, we employ the distilled MiniLM model, fine-tuned on domain-specific data, for high-precision answer extraction. Our approach is evaluated across three configurations: scholarly document abstract retrieval, gold-standard scholarly documents abstract, and gold-standard snippets, consistently outperforming established methods such as RYGH and bio-answer finder. Notably, we demonstrate that extracting answers from scholarly documents abstracts alone can yield high accuracy, underscoring the sufficiency of abstracts for many biomedical queries. Despite its compact size, MiniLM exhibits competitive performance, challenging the prevailing notion that only large, resource-intensive models can handle such complex tasks. Our results, validated across various question types and evaluation batches, highlight the robustness and adaptability of our method in real-world biomedical applications. While our approach shows promise, we identify challenges in handling complex list-type questions and inconsistencies in evaluation metrics. Future work will focus on refining the topic model with more extensive domain-specific datasets, further optimizing MiniLM and utilizing large language models (LLM) to improve both precision and efficiency in biomedical question answering.

Domain Generation Algorithms (DGAs) are malicious techniques used by malware to dynamically generate seemingly random domain names for communication with Command & Control (C&C) servers. Due to the fast and simple generation of DGA domains, detection methods must be highly efficient and precise to be effective. Large Language Models (LLMs) have demonstrated their proficiency in real-time detection tasks, making them ideal candidates for detecting DGAs. Our work validates the effectiveness of fine-tuned LLMs for detecting DGAs and DNS exfiltration attacks. We developed LLM models and conducted comprehensive evaluation using a diverse dataset comprising 59 distinct real-world DGA malware families and normal domain data. Our LLM model significantly outperformed traditional natural language processing techniques, especially in detecting unknown DGAs. We also evaluated its performance on DNS exfiltration datasets, demonstrating its effectiveness in enhancing cybersecurity measures. To the best of our knowledge, this is the first work that empirically applies LLMs for DGA and DNS exfiltration detection., Comment: Accepted in Proceedings of the Workshop at AI for Cyber Threat Intelligence (WAITI), 2024

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks, which poses a critical problem. These attacks target LLMs applications through using carefully designed input prompts to divert the model from adhering to original instruction, thereby it could execute unintended actions. These manipulations pose serious security threats which potentially results in data leaks, biased outputs, or harmful responses. This project explores the security vulnerabilities in relation to prompt injection attacks. To detect whether a prompt is vulnerable or not, we follows two approaches: 1) a pre-trained LLM, and 2) a fine-tuned LLM. Then, we conduct a thorough analysis and comparison of the classification performance. Firstly, we use pre-trained XLM-RoBERTa model to detect prompt injections using test dataset without any fine-tuning and evaluate it by zero-shot classification. Then, this proposed work will apply supervised fine-tuning to this pre-trained LLM using a task-specific labeled dataset from deepset in huggingface, and this fine-tuned model achieves impressive results with 99.13\% accuracy, 100\% precision, 98.33\% recall and 99.15\% F1-score thorough rigorous experimentation and evaluation. We observe that our approach is highly efficient in detecting prompt injection attacks.

We explore red stellar populations toward the W3 giant molecular cloud through the use of optical-to-infrared (IR) photometry and Gaia DR 3 data, simultaneously characterizing stellar content and properties of dust in the molecular medium. We use a Rayleigh-Jeans Color Excess (RJCE) method modified to de-redden stellar observations of both red giants (RGs) and OB stars, and construct an IR Hertzsprung-Russell diagram validated against the Besanccon Galactic model. Taking advantage of the near-universal IR interstellar extinction law and precise Gaia measurements, we develop a method for obtaining the spectral classification, foreground extinction, and distance moduli of stars, validated by spectroscopically-confirmed OB stars. We constrain the observed parallax and proper motion of OB stars in W3, demonstrating the importance of considering systematic effects in the parallax bias, and assign parallax- and proper motion-based cloud membership to our stellar samples. While it has been assumed that all spectroscopic OB stars are inside the W3 cloud, we find evidence of seven background B stars and three potential runaway OB stars. The methods developed here based on known stellar populations enable us to identify 82 new OB candidates that are confidently within the cloud. We quantify several dust-to-dust empirical correlations, in particular the IR color excess $E(H-[4.5])$ and the optical depth $\tau_1$ of submillimeter dust emission at 1 THz using RGs behind W3, measuring a best fit of $E(H-[4.5]) = (1.07 \pm 0.04) \times 10^3 \, \tau_{1,\,\mathrm{HOTT}} + (0.00 \pm 0.02)$ mags., Comment: accepted for publication in ApJ, 39 pages, 20 figures

A basic question about the directed landscape is how much of it can be reconstructed simply by knowing the shapes of its geodesics. We prove that the directed landscape can be reconstructed from the shapes of its semi-infinite geodesics. In order to show this result, we make use of the Busemann process of the directed landscape together with a novel ``coordinate system" and ``differential distance" to capture the behaviour of semi-infinite geodesics.

Consider the math problem: "Lily received 3 cookies from her best friend yesterday and ate 5 for breakfast. Today, her friend gave her 3 more cookies. How many cookies does Lily have now?" Many large language models (LLMs) in previous research approach this problem by calculating the answer "1" using the equation "3 - 5 + 3." However, from a human perspective, we recognize the inherent flaw in this problem: Lily cannot eat 5 cookies if she initially only had 3. This discrepancy prompts a key question: Are current LLMs merely Blind Solver that apply mathematical operations without deeper reasoning, or can they function as Logical Thinker capable of identifying logical inconsistencies? To explore this question, we propose a benchmark dataset, FaultyMath, which includes faulty math problems of rich diversity: i) multiple mathematical categories, e.g., algebra, geometry, number theory, etc., ii) varying levels of difficulty, and iii) different origins of faultiness -- ranging from violations of common sense and ambiguous statements to mathematical contradictions and more. We evaluate a broad spectrum of LLMs, including open-source, closed-source, and math-specialized models, using FaultyMath across three dimensions: (i) How accurately can the models detect faulty math problems without being explicitly prompted to do so? (ii) When provided with hints -- either correct or misleading -- about the validity of the problems, to what extent do LLMs adapt to become reliable Logical Thinker? (iii) How trustworthy are the explanations generated by LLMs when they recognize a math problem as flawed? Through extensive experimentation and detailed analysis, our results demonstrate that existing LLMs largely function as Blind Solver and fall short of the reasoning capabilities required to perform as Logical Thinker.

Climate change poses critical challenges globally, disproportionately affecting low-income countries that often lack resources and linguistic representation on the international stage. Despite Bangladesh's status as one of the most vulnerable nations to climate impacts, research gaps persist in Bengali-language studies related to climate change and NLP. To address this disparity, we introduce Dhoroni, a novel Bengali (Bangla) climate change and environmental news dataset, comprising a 2300 annotated Bangla news articles, offering multiple perspectives such as political influence, scientific/statistical data, authenticity, stance detection, and stakeholder involvement. Furthermore, we present an in-depth exploratory analysis of Dhoroni and introduce BanglaBERT-Dhoroni family, a novel baseline model family for climate and environmental opinion detection in Bangla, fine-tuned on our dataset. This research contributes significantly to enhancing accessibility and analysis of climate discourse in Bengali (Bangla), addressing crucial communication and research gaps in climate-impacted regions like Bangladesh with 180 million people., Comment: In Review

Metaheuristic search methods have proven to be essential tools for tackling complex optimization challenges, but their full potential is often constrained by conventional algorithmic frameworks. In this paper, we introduce a novel approach called Deep Heuristic Search (DHS), which models metaheuristic search as a memory-driven process. DHS employs multiple search layers and memory-based exploration-exploitation mechanisms to navigate large, dynamic search spaces. By utilizing model-free memory representations, DHS enhances the ability to traverse temporal trajectories without relying on probabilistic transition models. The proposed method demonstrates significant improvements in search efficiency and performance across a range of heuristic optimization problems., Comment: 10 pages, 6 figures

Data imputation addresses the challenge of imputing missing values in database instances, ensuring consistency with the overall semantics of the dataset. Although several heuristics which rely on statistical methods, and ad-hoc rules have been proposed. These do not generalise well and often lack data context. Consequently, they also lack explainability. The existing techniques also mostly focus on the relational data context making them unsuitable for wider application contexts such as in graph data. In this paper, we propose a graph data imputation approach called GIG which relies on graph differential dependencies (GDDs). GIG, learns the GDDs from a given knowledge graph, and uses these rules to train a transformer model which then predicts the value of missing data within the graph. By leveraging GDDs, GIG incoporates semantic knowledge into the data imputation process making it more reliable and explainable. Experimental results on seven real-world datasets highlight GIG's effectiveness compared to existing state-of-the-art approaches., Comment: 12 pages, 4 figures, published to ADC

Large Language Models (LLMs) have demonstrated remarkable success as general-purpose task solvers across various fields, including NLP, healthcare, finance, and law. However, their capabilities remain limited when addressing domain-specific problems, particularly in downstream NLP tasks. Research has shown that models fine-tuned on instruction-based downstream NLP datasets outperform those that are not fine-tuned. While most efforts in this area have primarily focused on resource-rich languages like English and broad domains, little attention has been given to multilingual settings and specific domains. To address this gap, this study focuses on developing a specialized LLM, LlamaLens, for analyzing news and social media content in a multilingual context. To the best of our knowledge, this is the first attempt to tackle both domain specificity and multilinguality, with a particular focus on news and social media. Our experimental setup includes 19 tasks, represented by 52 datasets covering Arabic, English, and Hindi. We demonstrate that LlamaLens outperforms the current state-of-the-art (SOTA) on 16 testing sets, and achieves comparable performance on 10 sets. We make the models and resources publicly available for the research community.(https://huggingface.co/QCRI), Comment: LLMs, Multilingual, Language Diversity, Large Language Models, Social Media, News Media, Specialized LLMs, Fact-checking, Media Analysis

The financial sector's dependence on digital infrastructure increases its vulnerability to cybersecurity threats, requiring strong IT security protocols with other entities. This collaboration, however, is often identified as the most vulnerable link in the chain of cybersecurity. Adopting both symbolic and substantive measures lessens the impact of IT security spending on decreasing the frequency of data security breaches in the long run. The Protection Motivation Theory clarifies actions triggered by data sharing with other organizations, and the Institutional theory aids in comprehending the intricate relationship between transparency and organizational conduct. We investigate how things like regulatory pressure, teamwork among institutions, and people's motivations to protect themselves influence cybersecurity. By using simple theories to understand these factors, this research aims to provide insights that can help financial institutions make better decisions to protect. We have also included the discussion, conclusion, and future directions in regard to collaboration in financial sector cybersecurity for exploring impact of resource sharing., Comment: 8 pages, 2 figures

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual information for precise speech representations. Existing speech representations generally fall into two categories: acoustic tokens from audio codecs and semantic tokens from speech self-supervised learning models. Although recent efforts have unified acoustic and semantic tokens for improved performance, they overlook the crucial role of contextual representation in comprehensive speech modeling. Our empirical investigations reveal that the absence of contextual representations results in elevated Word Error Rate (WER) and Word Information Lost (WIL) scores in speech transcriptions. To address these limitations, we propose two novel distillation approaches: (1) a language model (LM)-guided distillation method that incorporates contextual information, and (2) a combined LM and self-supervised speech model (SM)-guided distillation technique that effectively distills multimodal representations (acoustic, semantic, and contextual) into a comprehensive speech tokenizer, termed DM-Codec. The DM-Codec architecture adopts a streamlined encoder-decoder framework with a Residual Vector Quantizer (RVQ) and incorporates the LM and SM during the training process. Experiments show DM-Codec significantly outperforms state-of-the-art speech tokenization models, reducing WER by up to 13.46%, WIL by 9.82%, and improving speech quality by 5.84% and intelligibility by 1.85% on the LibriSpeech benchmark dataset. The code, samples, and model checkpoints are available at https://github.com/mubtasimahasan/DM-Codec.

Visual Question Answer (VQA) poses the problem of answering a natural language question about a visual context. Bangla, despite being a widely spoken language, is considered low-resource in the realm of VQA due to the lack of a proper benchmark dataset. The absence of such datasets challenges models that are known to be performant in other languages. Furthermore, existing Bangla VQA datasets offer little cultural relevance and are largely adapted from their foreign counterparts. To address these challenges, we introduce a large-scale Bangla VQA dataset titled ChitroJera, totaling over 15k samples where diverse and locally relevant data sources are used. We assess the performance of text encoders, image encoders, multimodal models, and our novel dual-encoder models. The experiments reveal that the pre-trained dual-encoders outperform other models of its scale. We also evaluate the performance of large language models (LLMs) using prompt-based techniques, with LLMs achieving the best performance. Given the underdeveloped state of existing datasets, we envision ChitroJera expanding the scope of Vision-Language tasks in Bangla.

Evaluating machine-generated text remains a significant challenge in NLP, especially for non-English languages. Current methodologies, including automated metrics, human assessments, and LLM-based evaluations, predominantly focus on English, revealing a significant gap in multilingual evaluation frameworks. We introduce the Cross Lingual Auto Evaluation (CIA) Suite, an extensible framework that includes evaluator LLMs (Hercule) and a novel test set (Recon) specifically designed for multilingual evaluation. Our test set features 500 human-annotated instructions spanning various task capabilities along with human judgment scores across six languages. This would enable benchmarking of general-purpose multilingual LLMs and facilitate meta-evaluation of Evaluator LLMs. The proposed model, Hercule, is a cross-lingual evaluation model that addresses the scarcity of reference answers in the target language by learning to assign scores to responses based on easily available reference answers in English. Our experiments demonstrate that Hercule aligns more closely with human judgments compared to proprietary models, demonstrating the effectiveness of such cross-lingual evaluation in low resource scenarios. Further, it is also effective in zero-shot evaluation on unseen languages. This study is the first comprehensive examination of cross-lingual evaluation using LLMs, presenting a scalable and effective approach for multilingual assessment. All code, datasets, and models will be publicly available to enable further research in this important area.

The proliferation of transliterated texts in digital spaces has emphasized the need for detecting and classifying hate speech in languages beyond English, particularly in low-resource languages. As online discourse can perpetuate discrimination based on target groups, e.g. gender, religion, and origin, multi-label classification of hateful content can help in comprehending hate motivation and enhance content moderation. While previous efforts have focused on monolingual or binary hate classification tasks, no work has yet addressed the challenge of multi-label hate speech classification in transliterated Bangla. We introduce BanTH, the first multi-label transliterated Bangla hate speech dataset comprising 37.3k samples. The samples are sourced from YouTube comments, where each instance is labeled with one or more target groups, reflecting the regional demographic. We establish novel transformer encoder-based baselines by further pre-training on transliterated Bangla corpus. We also propose a novel translation-based LLM prompting strategy for transliterated text. Experiments reveal that our further pre-trained encoders are achieving state-of-the-art performance on the BanTH dataset, while our translation-based prompting outperforms other strategies in the zero-shot setting. The introduction of BanTH not only fills a critical gap in hate speech research for Bangla but also sets the stage for future exploration into code-mixed and multi-label classification challenges in underrepresented languages.

Inverse Synthetic Aperture Radar (ISAR) imaging presents a formidable challenge when it comes to small everyday objects due to their limited Radar Cross-Section (RCS) and the inherent resolution constraints of radar systems. Existing ISAR reconstruction methods including backprojection (BP) often require complex setups and controlled environments, rendering them impractical for many real-world noisy scenarios. In this paper, we propose a novel Analysis-through-Synthesis (ATS) framework enabled by Neural Radiance Fields (NeRF) for high-resolution coherent ISAR imaging of small objects using sparse and noisy Ultra-Wideband (UWB) radar data with an inexpensive and portable setup. Our end-to-end framework integrates ultra-wideband radar wave propagation, reflection characteristics, and scene priors, enabling efficient 2D scene reconstruction without the need for costly anechoic chambers or complex measurement test beds. With qualitative and quantitative comparisons, we demonstrate that the proposed method outperforms traditional techniques and generates ISAR images of complex scenes with multiple targets and complex structures in Non-Line-of-Sight (NLOS) and noisy scenarios, particularly with limited number of views and sparse UWB radar scans. This work represents a significant step towards practical, cost-effective ISAR imaging of small everyday objects, with broad implications for robotics and mobile sensing applications.

Recent advancements in Artificial Intelligence (AI) algorithms have sparked a race to enhance hardware capabilities for accelerated task processing. While significant strides have been made, particularly in areas like computer vision, the progress of AI algorithms appears to have outpaced hardware development, as specialized hardware struggles to keep up with the ever-expanding algorithmic landscape. To address this gap, we propose a new accelerator architecture, called messaging-based intelligent processing unit (m-IPU), capable of runtime configuration to cater to various AI tasks. Central to this hardware is a programmable interconnection mechanism, relying on message passing between compute elements termed Sites. While the messaging between compute elements is a known concept for Network-on-Chip or multi-core architectures, our hardware can be categorized as a new class of coarse-grained reconfigurable architecture (CGRA), specially optimized for AI workloads. In this paper, we highlight m-IPU's fundamental advantages for machine learning applications. We illustrate the efficacy through implementations of a neural network, matrix multiplications, and convolution operations, showcasing lower latency compared to the state-of-the-art. Our simulation-based experiments, conducted on the TSMC 28nm technology node, reveal minimal power consumption of 44.5 mW with 94,200 cells utilization. For 3D convolution operations on (32 x 128) images, each (256 x 256), using a (3 x 3) filter and 4,096 Sites at a frequency of 100 MHz, m-IPU achieves processing in just 503.3 milliseconds. These results underscore the potential of m-IPU as a unified, scalable, and high-performance hardware architecture tailored for future AI applications., Comment: 12 Pages, 8 Figures, Journal

Recent advancements in transformer models have yielded impressive results in Non-Intrusive Load Monitoring (NILM). However, effectively training a transformer on small-scale datasets remains a challenge. This paper addresses this issue by enhancing the attention mechanism of the original transformer to improve performance. We propose two novel mechanisms: the inter-token relation enhancement mechanism and the dynamic temperature tuning mechanism. The first mechanism reduces the prioritization of intra-token relationships in the token similarity matrix during training, thereby increasing inter-token focus. The second mechanism introduces a learnable temperature tuning for the token similarity matrix, mitigating the over-smoothing problem associated with fixed temperature values. Both mechanisms are supported by rigorous mathematical foundations. We evaluate our approach using the REDD residential NILM dataset, a relatively small-scale dataset and demonstrate that our methodology significantly enhances the performance of the original transformer model across multiple appliance types., Comment: Submitted to 27th IEEE-ICCIT

The advancement of artificial intelligence (AI) in food and nutrition research is hindered by a critical bottleneck: the lack of annotated food data. Despite the rise of highly efficient AI models designed for tasks such as food segmentation and classification, their practical application might necessitate proficiency in AI and machine learning principles, which can act as a challenge for non-AI experts in the field of nutritional sciences. Alternatively, it highlights the need to translate AI models into user-friendly tools that are accessible to all. To address this, we present a demo of a semi-automatic food image annotation tool leveraging the Segment Anything Model (SAM). The tool enables prompt-based food segmentation via user interactions, promoting user engagement and allowing them to further categorise food items within meal images and specify weight/volume if necessary. Additionally, we release a fine-tuned version of SAM's mask decoder, dubbed MealSAM, with the ViT-B backbone tailored specifically for food image segmentation. Our objective is not only to contribute to the field by encouraging participation, collaboration, and the gathering of more annotated food data but also to make AI technology available for a broader audience by translating AI into practical tools., Comment: Accepted Demo Paper - ECAI 2024

Recent advances in deep learning for processing point clouds hold increased interest in Few-Shot Class Incremental Learning (FSCIL) for 3D computer vision. This paper introduces a new method to tackle the Few-Shot Continual Incremental Learning (FSCIL) problem in 3D point cloud environments. We leverage a foundational 3D model trained extensively on point cloud data. Drawing from recent improvements in foundation models, known for their ability to work well across different tasks, we propose a novel strategy that does not require additional training to adapt to new tasks. Our approach uses a dual cache system: first, it uses previous test samples based on how confident the model was in its predictions to prevent forgetting, and second, it includes a small number of new task samples to prevent overfitting. This dynamic adaptation ensures strong performance across different learning tasks without needing lots of fine-tuning. We tested our approach on datasets like ModelNet, ShapeNet, ScanObjectNN, and CO3D, showing that it outperforms other FSCIL methods and demonstrating its effectiveness and versatility. The code is available at \url{https://github.com/ahmadisahar/ACCV_FCIL3D}., Comment: ACCV 2024

We present a comprehensive survey on the use of annotations in information visualizations, highlighting their crucial role in improving audience understanding and engagement with visual data. Our investigation encompasses empirical studies on annotations, showcasing their impact on user engagement, interaction, comprehension, and memorability across various contexts. We also study the existing tools and techniques for creating annotations and their diverse applications, enhancing the understanding of both practical and theoretical aspects of annotations in data visualization. Additionally, we identify existing research gaps and propose potential future research directions, making our survey a valuable resource for researchers, visualization designers, and practitioners by providing a thorough understanding of the application of annotations in visualization.

Text-to-image (T2I) models are increasingly used in impactful real-life applications. As such, there is a growing need to audit these models to ensure that they generate desirable, task-appropriate images. However, systematically inspecting the associations between prompts and generated content in a human-understandable way remains challenging. To address this, we propose \emph{Concept2Concept}, a framework where we characterize conditional distributions of vision language models using interpretable concepts and metrics that can be defined in terms of these concepts. This characterization allows us to use our framework to audit models and prompt-datasets. To demonstrate, we investigate several case studies of conditional distributions of prompts, such as user defined distributions or empirical, real world distributions. Lastly, we implement Concept2Concept as an open-source interactive visualization tool facilitating use by non-technical end-users. Warning: This paper contains discussions of harmful content, including CSAM and NSFW material, which may be disturbing to some readers.

This paper presents a comprehensive study on the tokenization techniques employed by state-of-the-art large language models (LLMs) and their implications on the cost and availability of services across different languages, especially low resource languages. The analysis considers multiple LLMs, including GPT-4 (using cl100k_base embeddings), GPT-3 (with p50k_base embeddings), and DaVinci (employing r50k_base embeddings), as well as the widely used BERT base tokenizer. The study evaluates the tokenization variability observed across these models and investigates the challenges of linguistic representation in subword tokenization. The research underscores the importance of fostering linguistically-aware development practices, especially for languages that are traditionally under-resourced. Moreover, this paper introduces case studies that highlight the real-world implications of tokenization choices, particularly in the context of electronic health record (EHR) systems. This research aims to promote generalizable Internationalization (I18N) practices in the development of AI services in this domain and beyond, with a strong emphasis on inclusivity, particularly for languages traditionally underrepresented in AI applications.

Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture long-range dependencies without complex architectural modifications. In contrast, ViTs effectively model global relationships but suffer from high computational costs due to the quadratic complexity of their self-attention mechanisms. Mamba addresses these limitations by leveraging Selective Structured State Space Models to effectively capture long-range dependencies with linear computational complexity. This survey analyzes the unique contributions, computational benefits, and applications of Mamba models while also identifying challenges and potential future research directions. We provide a foundational resource for advancing the understanding and growth of Mamba models in computer vision. An overview of this work is available at https://github.com/maklachur/Mamba-in-Computer-Vision., Comment: Under Review

Anomaly detection in clinical time-series holds significant potential in identifying suspicious patterns in different biological parameters. In this paper, we propose a targeted method that incorporates the clinical domain knowledge into LLMs to improve their ability to detect anomalies. We introduce the Metabolism Pathway-driven Prompting (MPP) method, which integrates the information about metabolic pathways to better capture the structural and temporal changes in biological samples. We applied our method for doping detection in sports, focusing on steroid metabolism, and evaluated using real-world data from athletes. The results show that our method improves anomaly detection performance by leveraging metabolic context, providing a more nuanced and accurate prediction of suspicious samples in athletes' profiles.

Transformer models have demonstrated impressive performance in Non-Intrusive Load Monitoring (NILM) applications in recent years. Despite their success, existing studies have not thoroughly examined the impact of various hyper-parameters on model performance, which is crucial for advancing high-performing transformer models. In this work, a comprehensive series of experiments have been conducted to analyze the influence of these hyper-parameters in the context of residential NILM. This study delves into the effects of the number of hidden dimensions in the attention layer, the number of attention layers, the number of attention heads, and the dropout ratio on transformer performance. Furthermore, the role of the masking ratio has explored in BERT-style transformer training, providing a detailed investigation into its impact on NILM tasks. Based on these experiments, the optimal hyper-parameters have been selected and used them to train a transformer model, which surpasses the performance of existing models. The experimental findings offer valuable insights and guidelines for optimizing transformer architectures, aiming to enhance their effectiveness and efficiency in NILM applications. It is expected that this work will serve as a foundation for future research and development of more robust and capable transformer models for NILM., Comment: Accepted to 4th IEEE-ICISET

Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence, particularly when using open-source LLMs. To mitigate this gap, we introduce a novel framework, Open-RAG, designed to enhance reasoning capabilities in RAG with open-source LLMs. Our framework transforms an arbitrary dense LLM into a parameter-efficient sparse mixture of experts (MoE) model capable of handling complex reasoning tasks, including both single- and multi-hop queries. Open-RAG uniquely trains the model to navigate challenging distractors that appear relevant but are misleading. As a result, Open-RAG leverages latent learning, dynamically selecting relevant experts and integrating external knowledge effectively for more accurate and contextually relevant responses. In addition, we propose a hybrid adaptive retrieval method to determine retrieval necessity and balance the trade-off between performance gain and inference speed. Experimental results show that the Llama2-7B-based Open-RAG outperforms state-of-the-art LLMs and RAG models such as ChatGPT, Self-RAG, and Command R+ in various knowledge-intensive tasks. We open-source our code and models at https://openragmoe.github.io/, Comment: Accepted to EMNLP 2024 Findings. Website: https://openragmoe.github.io/. 14 pages, 7 figures, 5 tables

In today's digitally driven landscape, robust Information Technology (IT) risk assessment practices are essential for safeguarding systems, digital communication, and data. This paper introduces 'AssessITS', an actionable method designed to provide organizations with comprehensive guidelines for conducting IT and cybersecurity risk assessments. Drawing extensively from NIST 800-30 Rev 1, COBIT 5, and ISO 31000, 'AssessITS' bridges the gap between high-level theoretical standards and practical implementation challenges. The paper outlines a step-by-step methodology that organizations can simply adopt to systematically identify, analyze, and mitigate IT risks. By simplifying complex principles into actionable procedures, this framework equips practitioners with the tools needed to perform risk assessments independently, without too much reliance on external vendors. The guidelines are developed to be straightforward, integrating practical evaluation metrics that allow for the precise quantification of asset values, threat levels, vulnerabilities, and impacts on confidentiality, integrity, and availability. This approach ensures that the risk assessment process is not only comprehensive but also accessible, enabling decision-makers to implement effective risk mitigation strategies customized to their unique operational contexts. 'AssessITS' aims to enable organizations to enhance their IT security strength through practical, actionable guidance based on internationally recognized standards., Comment: 25 pages, 8 figures, 7 tables

This paper considers the Target Set Selection (TSS) Problem in social networks, a fundamental problem in viral marketing. In the TSS problem, a graph and a threshold value for each vertex of the graph are given. We need to find a minimum size vertex subset to "activate" such that all graph vertices are activated at the end of the propagation process. Specifically, we propose a novel approach called "a census-based genetic algorithm" for the TSS problem. In our algorithm, we use the idea of a census to gather and store information about each individual in a population and collect census data from the individuals constructed during the algorithm's execution so that we can achieve greater diversity and avoid premature convergence at locally optimal solutions. We use two distinct census information: (a) for each individual, the algorithm stores how many times it has been identified during the execution (b) for each network node, the algorithm counts how many times it has been included in a solution. The proposed algorithm can also self-adjust by using a parameter specifying the aggressiveness employed in each reproduction method. Additionally, the algorithm is designed to run in a parallelized environment to minimize the computational cost and check each individual's feasibility. Moreover, our algorithm finds the optimal solution in all cases while experimenting on random graphs. Furthermore, we execute the proposed algorithm on 14 large graphs of real-life social network instances from the literature, improving around 9.57 solution size (on average) and 134 vertices (in total) compared to the best solutions obtained in previous studies.

The development of large-scale quantum networks requires reliable quantum channels, the quality of which can be quantified by the framework of quantum process tomography. In this work, we leverage ancilla-assisted process tomography and Bayesian inference to probe a 1.6 km deployed fiber-optic link. We send one of two polarization-entangled photons from Alice in one building to Bob in another, exploiting the local qubit as an ancilla system to characterize the corresponding quantum channel. Monitoring over a 24 h period returns a steady process fidelity of 95.1(1)%, while controllable spectral filtering with passbands from 0.025-4.38 THz finds fidelities that first increase, then level off with bandwidth, suggesting both stable operation with time and minimal polarization mode dispersion. To our knowledge, these results represent the first AAPT of a deployed quantum link, revealing a valuable tool for in situ analysis of entanglement-based quantum networks.

The spread of misinformation through online social media platforms has had substantial societal consequences. As a result, platforms have introduced measures to alert users of news content that may be misleading or contain inaccuracies as a means to discourage them from sharing it. These interventions sometimes cite external sources, such as fact-checking organizations and news outlets, for providing assessments related to the accuracy of the content. However, it is unclear whether users trust the assessments provided by these entities and whether perceptions vary across different topics of news. We conducted an online study with 655 US participants to explore user perceptions of eight categories of fact-checking entities across two misinformation topics, as well as factors that may impact users' perceptions. We found that participants' opinions regarding the trustworthiness and bias of the entities varied greatly, aligning largely with their political preference. However, just the presence of a fact-checking label appeared to discourage participants from sharing the headlines studied. Our results hint at the need for further exploring fact-checking entities that may be perceived as neutral, as well as the potential for incorporating multiple assessments in such labels.

The geotechnical evaluation of seabed sediments is important for engineering projects and naval applications, offering valuable insights into sediment properties, behavior, and strength. Obtaining high-quality seabed samples can be a challenging task, making in-situ testing an essential part of site characterization. Free Fall Penetrometers (FFP) have emerged as robust tools for rapidly profiling seabed surface sediments, even in energetic nearshore or estuarine conditions and shallow as well as deep depths. While methods for interpretation of traditional offshore Cone Penetration Testing (CPT) data are well-established, their adaptation to FFP data is still an area of research. In this study, we introduce an innovative approach that utilizes machine learning algorithms to create a sediment behavior classification system based on portable free fall penetrometer (PFFP) data. The proposed model leverages PFFP measurements obtained from locations such as Sequim Bay (Washington), the Potomac River, and the York River (Virginia). The result shows 91.1\% accuracy in the class prediction, with the classes representing cohesionless sediment with little to no plasticity, cohesionless sediment with some plasticity, cohesive sediment with low plasticity, and cohesive sediment with high plasticity. The model prediction not only provides the predicted class but also yields an estimate of inherent uncertainty associated with the prediction, which can provide valuable insight about different sediment behaviors. These uncertainties typically range from very low to very high, with lower uncertainties being more common, but they can increase significantly dpending on variations in sediment composition, environmental conditions, and operational techniques. By quantifying uncertainty, the model offers a more comprehensive and informed approach to sediment classification.

Modern high-end systems are increasingly becoming heterogeneous, providing users options to use general purpose Graphics Processing Units (GPU) and other accelerators for additional performance. High Performance Computing (HPC) and Artificial Intelligence (AI) applications are often carefully arranged to overlap communications and computation for increased efficiency on such platforms. This has led to efforts to extend popular communication libraries to support GPU awareness and more recently, GPU-initiated operations. In this paper, we present Intel SHMEM, a library that enables users to write programs that are GPU aware, in that API calls support GPU memory, and also support GPU-initiated communication operations by embedding OpenSHMEM style calls within GPU kernels. We also propose thread-collaborative extensions to the OpenSHMEM standard that can enable users to better exploit the strengths of GPUs. Our implementation adapts to choose between direct load/store from GPU and the GPU copy engine based transfer to optimize performance on different configurations.

With the increasing adoption of AI-driven tools in software development, large language models (LLMs) have become essential for tasks like code generation, bug fixing, and optimization. Tools like ChatGPT, GitHub Copilot, and Codeium provide valuable assistance in solving programming challenges, yet their effectiveness remains underexplored. This paper presents a comparative study of ChatGPT, Codeium, and GitHub Copilot, evaluating their performance on LeetCode problems across varying difficulty levels and categories. Key metrics such as success rates, runtime efficiency, memory usage, and error-handling capabilities are assessed. GitHub Copilot showed superior performance on easier and medium tasks, while ChatGPT excelled in memory efficiency and debugging. Codeium, though promising, struggled with more complex problems. Despite their strengths, all tools faced challenges in handling harder problems. These insights provide a deeper understanding of each tool's capabilities and limitations, offering guidance for developers and researchers seeking to optimize AI integration in coding workflows.

Phishing attacks are a growing cybersecurity threat, leveraging deceptive techniques to steal sensitive information through malicious websites. To combat these attacks, this paper introduces PhishGuard, an optimal custom ensemble model designed to improve phishing site detection. The model combines multiple machine learning classifiers, including Random Forest, Gradient Boosting, CatBoost, and XGBoost, to enhance detection accuracy. Through advanced feature selection methods such as SelectKBest and RFECV, and optimizations like hyperparameter tuning and data balancing, the model was trained and evaluated on four publicly available datasets. PhishGuard outperformed state-of-the-art models, achieving a detection accuracy of 99.05% on one of the datasets, with similarly high results across other datasets. This research demonstrates that optimization methods in conjunction with ensemble learning greatly improve phishing detection performance.

Brownian last passage percolation is a classical model of integrable probability and the KPZ universality class. We consider the Brownian last passage model with a functional initial condition: $$BLPP(X;(t,m)) = \max_{0 \leq t_0 \leq t_1 \leq \cdots \leq t_m = t} X(t_0) + \sum_{k=1}^m B_k(t_k) - B_k(t_{k-1}).$$ Here $X: [0,1] \to \mathbb{R}$ and $B_k$ are independent, standard Brownian motions. We derive a formula for finite dimensional laws of $t \mapsto BLPP(X;(t,m))$ in terms of a Fredholm determinant.

With the remarkable capability to reach the public instantly, social media has become integral in sharing scholarly articles to measure public response. Since spamming by bots on social media can steer the conversation and present a false public interest in given research, affecting policies impacting the public's lives in the real world, this topic warrants critical study and attention. We used the Altmetric dataset in combination with data collected through the Twitter Application Programming Interface (API) and the Botometer API. We combined the data into an extensive dataset with academic articles, several features from the article and a label indicating whether the article had excessive bot activity on Twitter or not. We analyzed the data to see the possibility of bot activity based on different characteristics of the article. We also trained machine-learning models using this dataset to identify possible bot activity in any given article. Our machine-learning models were capable of identifying possible bot activity in any academic article with an accuracy of 0.70. We also found that articles related to "Health and Human Science" are more prone to bot activity compared to other research areas. Without arguing the maliciousness of the bot activity, our work presents a tool to identify the presence of bot activity in the dissemination of an academic article and creates a baseline for future research in this direction., Comment: 38 pages, 10 figures. Aslib Journal of Information Management, Vol. ahead-of-print No. ahead-of-print

As edge computing and the Internet of Things (IoT) expand, horizontal collaboration (HC) emerges as a distributed data processing solution for resource-constrained devices. In particular, a convolutional neural network (CNN) model can be deployed on multiple IoT devices, allowing distributed inference execution for image recognition while ensuring model and data privacy. Yet, this distributed architecture remains vulnerable to adversaries who want to make subtle alterations that impact the model, even if they lack access to the entire model. Such vulnerabilities can have severe implications for various sectors, including healthcare, military, and autonomous systems. However, security solutions for these vulnerabilities have not been explored. This paper presents a novel framework for Secure Horizontal Edge with Adversarial Threat Handling (SHEATH) to detect adversarial noise and eliminate its effect on CNN inference by recovering the original feature maps. Specifically, SHEATH aims to address vulnerabilities without requiring complete knowledge of the CNN model in HC edge architectures based on sequential partitioning. It ensures data and model integrity, offering security against adversarial attacks in diverse HC environments. Our evaluations demonstrate SHEATH's adaptability and effectiveness across diverse CNN configurations.

The National Bridge Inspection Standards require detailed element-level bridge inspections. Traditionally, inspectors manually assign condition ratings by rating structural components based on damage, but this process is labor-intensive and time-consuming. Automating the element-level bridge inspection process can facilitate more comprehensive condition documentation to improve overall bridge management. While semantic segmentation of bridge point clouds has been studied, research on instance segmentation of bridge elements is limited, partly due to the lack of annotated datasets, and the difficulty in generalizing trained models. To address this, we propose a novel approach for generating synthetic data using three distinct methods. Our framework leverages the Mask3D transformer model, optimized with hyperparameter tuning and a novel occlusion technique. The model achieves state-of-the-art performance on real LiDAR and photogrammetry bridge point clouds, respectively, demonstrating the potential of the framework for automating element-level bridge inspections., Comment: 33 pages, 12 figures, Submitted to "Automation in Construction"

Speech recordings are being more frequently used to detect and monitor disease, leading to privacy concerns. Beyond cryptography, protection of speech can be addressed by approaches, such as perturbation, disentanglement, and re-synthesis, that eliminate sensitive information of the speaker, leaving the information necessary for medical analysis purposes. In order for such privacy protective approaches to be developed, clear and systematic specifications of assumptions concerning medical settings and the needs of medical professionals are necessary. In this paper, we propose a Scenario of Use Scheme that incorporates an Attacker Model, which characterizes the adversary against whom the speaker's privacy must be defended, and a Protector Model, which specifies the defense. We discuss the connection of the scheme with previous work on speech privacy. Finally, we present a concrete example of a specified Scenario of Use and a set of experiments about protecting speaker data against gender inference attacks while maintaining utility for Parkinson's detection., Comment: Accepted and published at SPSC Symposium 2024 4th Symposium on Security and Privacy in Speech Communication. Interspeech 2024