Search arXiv⌕ Search

arXiv subjects

Michael Fire

Publications and source records attributed to Michael Fire.

At least 19 recordsLinked to original sources
arXiv2026

Stylometric Defenses Against Author Impersonation in Software Repositories

Software supply-chain attacks increasingly exploit an identity gap where compromised maintainer accounts authorize malicious changes. This work evaluates patch-level authorship verification as a behavioral defense layer, showing that stylometric analysis can operate not only on full source files but also on patch-level commits. We fine-tune a cross-modal transformer on more than 20 years of Linux kernel commit history to embed code diffs and commit messages into a unified stylometric space, achieving ROC AUC of 0.93 for open-world authorship verification. We then use these representations in a streaming anomaly detector suited to continuous integration and deployment (CI/CD) settings. We validate the pipeline on two retrospective supply-chain incidents involving different patch characteristics: the 2021 PHP backdoor and the 2026 ForceMemo/GlassWorm campaign. Without retraining, the proposed detector surfaces both PHP forged commits within approximately 1% of the maintainer audit queue and ranks the 28 scoreable ForceMemo spoofs with a median per-repository review burden of 0.8%. These results indicate that cross-modal patch-level embeddings can support behavioral triage against author impersonation in real-world repositories.

cs.CR↗
arXiv2026

Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups

Large Language Models (LLMs) are increasingly shaping how we consume information and form our worldview. This raises concerns beyond bias in AI: do LLMs grasp the emotional nuances conveyed via textual framing? In this work, we empirically evaluate how well an array of LLMs aligns with human emotional perception. Considering news headlines covering political and geopolitical conflicts, both human participants (n = 3011, a representative sample of the U.K. adult population, via a YouGov survey) and seven LLMs answered whether headlines evoked sympathy for a specified side in a conflict. We find that the correlation between AI and human evaluations varies across models, ranging from very high (0.789, GPT-5.2) to medium (0.4 ,Mistral Large 2512). Crucially, the leading models are broadly aligned with human judgments across all demographic subgroups, including age, gender, level of education, prior geopolitical knowledge, and participants' predispositions regarding the conflict, although there are statistically significant differences between groups. This research, with its robust design and large, demographically diverse dataset, offers the most comprehensive evaluation of LLMs' comprehension of news framing to date. Findings highlight an important, often-ignored aspect of differential alignment: even when aggregate performance is high, AI alignment is not universal -- it may correspond differently with demographic features and cultural norms. Considering or ignoring the need for differential alignment may therefore have significant implications for the development of ethical and useful AI systems.

cs.CL↗
arXiv2026

Gender Gap Analysis in News and Talk Online Radio Broadcast

Radio broadcasting remains a dominant medium of communication, reaching 82% of Americans ages 12 and older weekly. Given its broad media impact, gender representation on radio news and talk stations may play an important role in shaping social and cultural perceptions. In this study, we examined patterns of gender representation in radio broadcasts, focusing on gender-based differences in total speaking time, air-time allocation across the day, and participation across broadcast topics. The dataset comprises filtered recordings from 74 US news and talk radio stations, collected over a 24-hour period and yielding more than 1,400 hours of content. We analyzed the data using VANPY, an in-house voice-analysis framework that combines multi-channel radio recording with AI-based speaker diarization, gender classification, speech-to-text transcription, and topic analysis. The results revealed consistent gender differences in allocated broadcast time, with male speakers accounting for 77% of total speaking time (SD = 6.8%). This gap remained evident during commute periods, when female speaking time was approximately 7.5-9.5 minutes per hour, compared with approximately 30.6-32.9 minutes for male speakers. Topic analysis further showed male dominance across all examined content categories. Female representation was lowest in "Talk Show Segments", where women accounted for only 10.8% of speaking time. Even in "Entertainment News", where female representation was highest, women accounted for only 35.8% of speaking time. Beyond these findings on gender dynamics in broadcast media, VANPY is publicly available and provides a systematic approach for analyzing large-scale audio data. It can be applied not only to radio broadcasts, but also to other audio domains such as human-computer interaction, corporate communication, and security applications.

cs.CY↗
arXiv2026

Comparative Analysis of Polygon-Based and Global Machine Learning Models for Bus Occupancy Prediction

Accurate forecasting of bus ridership (passengers numbers) is crucial for efficient management and optimization of public transport systems. Traditional forecasting models often fail to capture the unique and localized dynamics of different urban areas by treating the entire city as a single, homogeneous region. This paper introduces a novel framework that enhances bus ridership prediction by integrating a spatial clustering methodology with multi-dimensional feature analysis. The proposed framework utilizes a diverse set of data, including bus ridership data (by route number, time, and bus stop) complemented by a variety of open source data, such as spatial features (e.g., attractive destinations), meteorological conditions (e.g., temperature, rainfall), and temporal patterns (e.g., time of day, day of week). By clustering the urban area into distinct regions, based on the principle that bus stops in close proximity share similar ridership characteristics, a separate local forecasting model is trained for each of these clusters. This localized approach demonstrates an accuracy comparable to that of global models. The findings suggest that a spatially-aware, localized modeling strategy is effective for public transport prediction, paving the way for more targeted and efficient service improvements.

cs.LG↗
arXiv2025

Studying Illustrations in Manuscripts: An Efficient Deep-Learning Approach

The recent Artificial Intelligence (AI) revolution has opened transformative possibilities for the humanities, particularly in unlocking the visual-artistic content embedded in historical illuminated manuscripts. While digital archives now offer unprecedented access to these materials, the ability to systematically locate, extract, and analyze illustrations at scale remains a major challenge. We present a general and scalable AI-based pipeline for large-scale visual analysis of illuminated manuscripts. The framework integrates modern deep-learning models for page-level illustration detection, illustration extraction, and multimodal description, enabling scholars to search, cluster, and study visual materials and artistic trends across entire corpora. We demonstrate the applicability of this approach on large heterogeneous collections, including the Vatican Library and richly illuminated manuscripts such as the Bible of Borso d'Este. The system reveals meaningful visual patterns and cross-manuscript relationships by embedding illustrations into a shared representation space and analyzing their similarity structure (see figure 4). By harnessing recent advances in computer vision and vision-language models, our framework enables new forms of large-scale visual scholarship in historical studies, art history, and cultural heritage making it possible to explore iconography, stylistic trends, and cultural connections in ways that were previously impractical.

cs.IR↗
arXiv2025

A Comprehensive Machine Learning Framework for Micromobility Demand Prediction

Dockless e-scooters, a key micromobility service, have emerged as eco-friendly and flexible urban transport alternatives. These services improve first and last-mile connectivity, reduce congestion and emissions, and complement public transport for short-distance travel. However, effective management of these services depends on accurate demand prediction, which is crucial for optimal fleet distribution and infrastructure planning. While previous studies have focused on analyzing spatial or temporal factors in isolation, this study introduces a framework that integrates spatial, temporal, and network dependencies for improved micromobility demand forecasting. This integration enhances accuracy while providing deeper insights into urban micromobility usage patterns. Our framework improves demand prediction accuracy by 27 to 49% over baseline models, demonstrating its effectiveness in capturing micromobility demand patterns. These findings support data-driven micromobility management, enabling optimized fleet distribution, cost reduction, and sustainable urban planning.

cs.LG↗
arXiv2025

Framework of Voting Prediction of Parliament Members

Keeping track of how lawmakers vote is essential for government transparency. While many parliamentary voting records are available online, they are often difficult to interpret, making it challenging to understand legislative behavior across parliaments and predict voting outcomes. Accurate prediction of votes has several potential benefits, from simplifying parliamentary work by filtering out bills with a low chance of passing to refining proposed legislation to increase its likelihood of approval. In this study, we leverage advanced machine learning and data analysis techniques to develop a comprehensive framework for predicting parliamentary voting outcomes across multiple legislatures. We introduce the Voting Prediction Framework (VPF) - a data-driven framework designed to forecast parliamentary voting outcomes at the individual legislator level and for entire bills. VPF consists of three key components: (1) Data Collection - gathering parliamentary voting records from multiple countries using APIs, web crawlers, and structured databases; (2) Parsing and Feature Integration - processing and enriching the data with meaningful features, such as legislator seniority, and content-based characteristics of a given bill; and (3) Prediction Models - using machine learning to forecast how each parliament member will vote and whether a bill is likely to pass. The framework will be open source, enabling anyone to use or modify the framework. To evaluate VPF, we analyzed over 5 million voting records from five countries - Canada, Israel, Tunisia, the United Kingdom and the USA. Our results show that VPF achieves up to 85% precision in predicting individual votes and up to 84% accuracy in predicting overall bill outcomes. These findings highlight VPF's potential as a valuable tool for political analysis, policy research, and enhancing public access to legislative decision-making.

cs.SI↗
arXiv2025

Dark LLMs: The Growing Threat of Unaligned AI Models

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to jailbreaking. The fundamental vulnerability of LLMs to jailbreak attacks stems from the very data they learn from. As long as this training data includes unfiltered, problematic, or 'dark' content, the models can inherently learn undesirable patterns or weaknesses that allow users to circumvent their intended safety controls. Our research identifies the growing threat posed by dark LLMs models deliberately designed without ethical guardrails or modified through jailbreak techniques. In our research, we uncovered a universal jailbreak attack that effectively compromises multiple state-of-the-art models, enabling them to answer almost any question and produce harmful outputs upon request. The main idea of our attack was published online over seven months ago. However, many of the tested LLMs were still vulnerable to this attack. Despite our responsible disclosure efforts, responses from major LLM providers were often inadequate, highlighting a concerning gap in industry practices regarding AI safety. As model training becomes more accessible and cheaper, and as open-source LLMs proliferate, the risk of widespread misuse escalates. Without decisive intervention, LLMs may continue democratizing access to dangerous knowledge, posing greater risks than anticipated.

cs.CL↗
arXiv2025

Behind the Byline: A Large-Scale Study of Scientific Author Contributions

Understanding how co-authors distribute credit is critical for accurately assessing scholarly collaboration. In this study, we uncover the implicit structures within scientific teamwork by systematically analyzing author contributions across a large corpus of research publications. We introduce a computational framework designed to convert free-text contribution statements into 14 standardized CRediT categories, identifying clear and consistent positional patterns in task assignments. By analyzing over 400,000 scientific articles from prominent sources such as PLOS One and Nature, we extracted and standardized more than 5.6 million author-task assignments corresponding to 1.58 million author mentions. Our analysis reveals substantial disparities in workload distribution. Notably, in small teams with three co-authors, the most engaged contributor performs over three times more tasks than the least engaged, a disparity that grows linearly with team size. This demonstrates a consistent pattern of central and peripheral roles within modern collaborative teams. Moreover, our analysis shows distinct positional biases in task allocation: technical responsibilities, such as software development and formal analysis, broadly fall to authors positioned earlier in the author list, whereas managerial tasks, including supervision and funding acquisition, increasingly concentrate among authors positioned toward the end. This gradient underscores a significant division of labor, where early-listed authors mainly undertake most hands-on activities. In contrast, senior authors mostly assume roles involving leadership and oversight. Our findings highlight the structured and hierarchical organization within scholarly collaborations, providing deeper insights into the specific roles and dynamics that govern academic teamwork

cs.DL↗
arXiv2025

VANPY: Voice Analysis Framework

Voice data is increasingly being used in modern digital communications, yet there is still a lack of comprehensive tools for automated voice analysis and characterization. To this end, we developed the VANPY (Voice Analysis in Python) framework for automated pre-processing, feature extraction, and classification of voice data. The VANPY is an open-source end-to-end comprehensive framework that was developed for the purpose of speaker characterization from voice data. The framework is designed with extensibility in mind, allowing for easy integration of new components and adaptation to various voice analysis applications. It currently incorporates over fifteen voice analysis components - including music/speech separation, voice activity detection, speaker embedding, vocal feature extraction, and various classification models. Four of the VANPY's components were developed in-house and integrated into the framework to extend its speaker characterization capabilities: gender classification, emotion classification, age regression, and height regression. The models demonstrate robust performance across various datasets, although not surpassing state-of-the-art performance. As a proof of concept, we demonstrate the framework's ability to extract speaker characteristics on a use-case challenge of analyzing character voices from the movie "Pulp Fiction." The results illustrate the framework's capability to extract multiple speaker characteristics, including gender, age, height, emotion type, and emotion intensity measured across three dimensions: arousal, dominance, and valence.

cs.SD↗
arXiv2024

Shaping History: Advanced Machine Learning Techniques for the Analysis and Dating of Cuneiform Tablets over Three Millennia

Cuneiform tablets, emerging in ancient Mesopotamia around the late fourth millennium BCE, represent one of humanity's earliest writing systems. Characterized by wedge-shaped marks on clay tablets, these artifacts provided insight into Mesopotamian civilization across various domains. Traditionally, the analysis and dating of these tablets rely on subjective assessment of shape and writing style, leading to uncertainties in pinpointing their exact temporal origins. Recent advances in digitization have revolutionized the study of cuneiform by enhancing accessibility and analytical capabilities. Our research uniquely focuses on the silhouette of tablets as significant indicators of their historical periods, diverging from most studies that concentrate on textual content. Utilizing an unprecedented dataset of over 94,000 images from the Cuneiform Digital Library Initiative collection, we apply deep learning methods to classify cuneiform tablets, covering over 3,000 years of history. By leveraging statistical, computational techniques, and generative modeling through Variational Auto-Encoders (VAEs), we achieve substantial advancements in the automatic classification of these ancient documents, focusing on the tablets' silhouettes as key predictors. Our classification approach begins with a Decision Tree using height-to-width ratios and culminates with a ResNet50 model, achieving a 61% macro F1-score for tablet silhouettes. Moreover, we introduce novel VAE-powered tools to enhance explainability and enable researchers to explore changes in tablet shapes across different eras and genres. This research contributes to document analysis and diplomatics by demonstrating the value of large-scale data analysis combined with statistical methods. These insights offer valuable tools for historians and epigraphists, enriching our understanding of cuneiform tablets and the cultures that produced them.

cs.CV↗
arXiv2024

A Novel Method for News Article Event-Based Embedding

Embedding news articles is a crucial tool for multiple fields, such as media bias detection, identifying fake news, and making news recommendations. However, existing news embedding methods are not optimized to capture the latent context of news events. Most embedding methods rely on full-text information and neglect time-relevant embedding generation. In this paper, we propose a novel lightweight method that optimizes news embedding generation by focusing on entities and themes mentioned in articles and their historical connections to specific events. We suggest a method composed of three stages. First, we process and extract events, entities, and themes from the given news articles. Second, we generate periodic time embeddings for themes and entities by training time-separated GloVe models on current and historical data. Lastly, we concatenate the news embeddings generated by two distinct approaches: Smooth Inverse Frequency (SIF) for article-level vectors and Siamese Neural Networks for embeddings with nuanced event-related information. We leveraged over 850,000 news articles and 1,000,000 events from the GDELT project to test and evaluate our method. We conducted a comparative analysis of different news embedding generation methods for validation. Our experiments demonstrate that our approach can both improve and outperform state-of-the-art methods on shared event detection tasks.

cs.CL↗
arXiv2023

Analyzing Key Users' behavior trends in Volunteer-Based Networks

Online social networks usage has increased significantly in the last decade and continues to grow in popularity. Multiple social platforms use volunteers as a central component. The behavior of volunteers in volunteer-based networks has been studied extensively in recent years. Here, we explore the development of volunteer-based social networks, primarily focusing on their key users' behaviors and activities. We developed two novel algorithms: the first reveals key user behavior patterns over time; the second utilizes machine learning methods to generate a forecasting model that can predict the future behavior of key users, including whether they will remain active donors or change their behavior to become mainly recipients, and vice-versa. These algorithms allowed us to analyze the factors that significantly influence behavior predictions. To evaluate our algorithms, we utilized data from over 2.4 million users on a peer-to-peer food-sharing online platform. Using our algorithm, we identified four main types of key user behavior patterns that occur over time. Moreover, we succeeded in forecasting future active donor key users and predicting the key users that would change their behavior to donors, with an accuracy of up to 89.6%. These findings provide valuable insights into the behavior of key users in volunteer-based social networks and pave the way for more effective communities-building in the future, while using the potential of machine learning for this goal.

cs.SI↗
arXiv2023

Short Run Transit Route Planning Decision Support System Using a Deep Learning-Based Weighted Graph

Public transport routing plays a crucial role in transit network design, ensuring a satisfactory level of service for passengers. However, current routing solutions rely on traditional operational research heuristics, which can be time-consuming to implement and lack the ability to provide quick solutions. Here, we propose a novel deep learning-based methodology for a decision support system that enables public transport (PT) planners to identify short-term route improvements rapidly. By seamlessly adjusting specific sections of routes between two stops during specific times of the day, our method effectively reduces times and enhances PT services. Leveraging diverse data sources such as GTFS and smart card data, we extract features and model the transportation network as a directed graph. Using self-supervision, we train a deep learning model for predicting lateness values for road segments. These lateness values are then utilized as edge weights in the transportation graph, enabling efficient path searching. Through evaluating the method on Tel Aviv, we are able to reduce times on more than 9\% of the routes. The improved routes included both intraurban and suburban routes showcasing a fact highlighting the model's versatility. The findings emphasize the potential of our data-driven decision support system to enhance public transport and city logistics, promoting greater efficiency and reliability in PT services.

cs.AI↗
arXiv2023

Interruptions detection in video conferences

In recent years, video conferencing (VC) popularity has skyrocketed for a wide range of activities. As a result, the number of VC users surged sharply. The sharp increase in VC usage has been accompanied by various newly emerging privacy and security challenges. VC meetings became a target for various security attacks, such as Zoombombing. Other VC-related challenges also emerged. For example, during COVID lockdowns, educators had to teach in online environments struggling with keeping students engaged for extended periods. In parallel, the amount of available VC videos has grown exponentially. Thus, users and companies are limited in finding abnormal segments in VC meetings within the converging volumes of data. Such abnormal events that affect most meeting participants may be indicators of interesting points in time, including security attacks or other changes in meeting climate, like someone joining a meeting or sharing a dramatic content. Here, we present a novel algorithm for detecting abnormal events in VC data. We curated VC publicly available recordings, including meetings with interruptions. We analyzed the videos using our algorithm, extracting time windows where abnormal occurrences were detected. Our algorithm is a pipeline that combines multiple methods in several steps to detect users' faces in each video frame, track face locations during the meeting and generate vector representations of a facial expression for each face in each frame. Vector representations are used to monitor changes in facial expressions throughout the meeting for each participant. The overall change in meeting climate is quantified using those parameters across all participants, and translating them into event anomaly detection. This is the first open pipeline for automatically detecting anomaly events in VC meetings. Our model detects abnormal events with 92.3% precision over the collected dataset.

cs.CV↗
arXiv2022

Open Framework for Analyzing Public Parliaments Data

Open information of government organizations is a subject that should interest all citizens who care about the functionality of their governments. Large-scale open governmental data open the door to new opportunities for citizens and researchers to monitor their government's activities and to improve its transparency. Over the years, various projects and systems have been processing and analyzing governmental data using open government information. Here, we present the Collecting and Analyzing Parliament Data (CAPD) framework. This novel generic open framework enables the collection and analysis of large-scale public governmental data from multiple sources. We used the framework to collect over 64,000 parliaments' protocols from over 90 committees from three countries. Then, we parsed the collected data and calculated structured features from it. Next, using the calculated features, we utilized anomaly detection and time series analysis to uncover various insights into the committees' activities. We demonstrate that the CAPD framework can be used to identify anomalous meetings and detect dates of events that affect the parliaments' functionality, and help to monitor their activities.

cs.SI↗
arXiv2022

Malicious Source Code Detection Using Transformer

Open source code is considered a common practice in modern software development. However, reusing other code allows bad actors to access a wide developers' community, hence the products that rely on it. Those attacks are categorized as supply chain attacks. Recent years saw a growing number of supply chain attacks that leverage open source during software development, relaying the download and installation procedures, whether automatic or manual. Over the years, many approaches have been invented for detecting vulnerable packages. However, it is uncommon to detect malicious code within packages. Those detection approaches can be broadly categorized as analyzes that use (dynamic) and do not use (static) code execution. Here, we introduce Malicious Source code Detection using Transformers (MSDT) algorithm. MSDT is a novel static analysis based on a deep learning method that detects real-world code injection cases to source code packages. In this study, we used MSDT and a dataset with over 600,000 different functions to embed various functions and applied a clustering algorithm to the resulting vectors, detecting the malicious functions by detecting the outliers. We evaluated MSDT's performance by conducting extensive experiments and demonstrated that our algorithm is capable of detecting functions that were injected with malicious code with precision@k values of up to 0.909.

cs.CR↗
arXiv2022

Ethnic Representation Analysis of Commercial Movie Posters

In the last decades, global awareness towards the importance of diverse representation has been increasing. Lack of diversity and discrimination toward minorities did not skip the film industry. Here, we examine ethnic bias in the film industry through commercial posters, the industry's primary advertisement medium for decades. Movie posters are designed to establish the viewer's initial impression. We developed a novel approach for evaluating ethnic bias in the film industry by analyzing nearly 125,000 posters using state-of-the-art deep learning models. Our analysis shows that while ethnic biases still exist, there is a trend of reduction of bias, as seen by several parameters. Particularly in English-speaking movies, the ethnic distribution of characters on posters from the last couple of years is reaching numbers that are approaching the actual ethnic composition of US population. An automatic approach to monitor ethnic diversity in the film industry, potentially integrated with financial value, may be of significant use for producers and policymakers.

cs.CY↗