检索结果-内蒙古大学图书馆

LLMCloudHunter: Harnessing LLMs for Automated Extraction of Detection Rules from Cloud-Based CTI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Schwartz, Yuval Benshimol, Lavi Mimran, Dudu Elovici, Yuval Shabtai, Asaf Department of Software and Information Systems Engineering Ben-Gurion University of the Negev

As the number and sophistication of cyber attacks have increased, threat hunting has become a critical aspect of active security, enabling proactive detection and mitigation of threats before they cause significant harm. Open-source cyber threat intelligence (OSCTI) is a valuable resource for threat hunters, however, it often comes in unstructured formats that require further manual analysis. Previous studies aimed at automating OSCTI analysis are limited since (1) they failed to provide actionable outputs, (2) they did not take advantage of images present in OSCTI sources, and (3) they focused on on-premises environments, overlooking the growing importance of cloud environments. To address these gaps, we propose LLMCloudHunter, a novel framework that leverages large language models (LLMs) to automatically generate generic-signature detection rule candidates from textual and visual OSCTI data. We evaluated the quality of the rules generated by the proposed framework using 12 annotated real-world cloud threat reports. The results show that our framework achieved a precision of 92% and recall of 98% for the task of accurately extracting API calls made by the threat actor and a precision of 99% with a recall of 98% for IoCs. Additionally, 99.18% of the generated detection rule candidates were successfully compiled and converted into Splunk queries. Copyright © 2024, The Authors. All rights reserved.

关键词： Quality control

Enhancing Secure Development in Globally Distributed software Product Lines: A Machine Learning-Powered Framework for Cyber-Resilient Ecosystems

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 5031-5049页

作者： Marya Iqbal Yaser Hafeez Nabil Almashfi Amjad Alsirhani Faeiz Alserhani Sadia Ali Mamoona Humayun Muhammad Jamal University Institute of Information Technology PMAS-Arid Agriculture UniversityRawalpindiPakistan Department of Software Engineering College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Department of Computer Science College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Department of Computer Engineering&Networks College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Department of Information Systems College of Computer and Information SciencesJouf UniversitySakakaAl Jouf72388Saudi Arabia Department of Mathematics Pir Mehr Ali Shah Arid Agriculture UniversityRawalpindiPakistan

Embracing software product lines(SPLs)is pivotal in the dynamic landscape of contemporary software ***,the flexibility and global distribution inherent in modern systems pose significant challenges to managing SPL variability,underscoring the critical importance of robust cybersecurity *** paper advocates for leveraging machine learning(ML)to address variability management issues and fortify the security of *** the context of the broader special issue theme on innovative cybersecurity approaches,our proposed ML-based framework offers an interdisciplinary perspective,blending insights from computing,social sciences,and ***,it employs ML for demand analysis,dynamic feature extraction,and enhanced feature selection in distributed settings,contributing to cyber-resilient *** experiments demonstrate the framework’s superiority,emphasizing its potential to boost productivity and security in *** digital threats evolve,this research catalyzes interdisciplinary collaborations,aligning with the special issue’s goal of breaking down academic barriers to strengthen digital ecosystems against sophisticated attacks while upholding ethics,privacy,and human values.

关键词： Machine Learning variability management cybersecurity digital ecosystems cyber-resilience

VANPY: Voice Analysis Framework

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Koushnir, Gregory Fire, Michael Alpert, Galit Fuhrmann Kagan, Dima Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Israel

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. Quantitatively, our gender classifier achieved 100% accuracy with no misses, height estimation resulted in a mean absolute error (MAE) of 5.5 cm for men and 10.2 cm for women, and age estimation yielded an MAE of 8.5 years for men and 9.9 years for women. Although emotion classification remains more challenging, our analysis discusses these results, indicating promising potential. © 2025, CC BY-NC-ND.

关键词： Speech analysis

Enhancing Soft Skills in Autistic Children: The Next Generation of Mind Champ's Technological Approach

学校读者我要写书评

暂无评论

Enhancing Soft Skills in Autistic Children: The Next Generat...

Advancements in Computing (ICAC), International Conference on

作者： Kalna Peiris Ruchira Nelaka Kalpani Manathunga Department of Computer Systems Engineering Department of Information Technology Department of Computer Science and Software Engineering

ISBN: (数字)9798331517878

ISBN: (纸本)9798331517885

Autism Spectrum Disorder (ASD) significantly impacts a child's ability to navigate social interactions, regulate emotions, and develop adaptive skills crucial for daily functioning. While various interventions exist to address cognitive and academic skills, the development of soft skills such as communication, emotional regulation, social interaction, and creativity remains an under explored area. This paper builds upon the foundational work of the Mind Champ platform, which originally targeted both learning and soft skills, by focusing exclusively on enhancing the soft skills development of autistic children. This enhanced version of the Mind Champ platform leverages advanced behavioral and emotional analysis techniques to offer a comprehensive technological solution. Through interactive activities centered on painting and music, the platform creates a structured, engaging, and supportive environment tailored to the unique needs of children with ASD. By prioritizing emotional engagement and creative expression, the platform empowers children to improve their social abilities, emotional regulation, and adaptability. The results from our continued research indicate that these technology-driven interventions contribute significantly to the holistic development of soft skills in autistic children, providing them with valuable tools to navigate social environments more effectively.

关键词： Autism Navigation Variable speed drives Motors Regulation Real-time systems Creativity Next generation networking Painting Resilience

MedConceptsQA: Open Source Medical Concepts QA Benchmark

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ben Shoham, Ofir Rappoport, Nadav Department of Software and Information Systems Engineering Ben-Gurion University of the Negev

We present MedConceptsQA, a dedicated open source benchmark for medical concepts question answering. The benchmark comprises of questions of various medical concepts across different vocabularies: diagnoses, procedures, and drugs. The questions are categorized into three levels of difficulty: easy, medium, and hard. We conducted evaluations of the benchmark using various Large Language Models. Our findings show that pre-trained clinical Large Language Models achieved accuracy levels close to random guessing on this benchmark, despite being pre-trained on medical data. However, GPT-4 achieves an absolute average improvement of nearly 27%-37% (27% for zero-shot learning and 37% for few-shot learning) when compared to clinical Large Language Models. Our benchmark serves as a valuable resource for evaluating the understanding and reasoning of medical concepts by Large Language Models. Our benchmark is available at https://***/datasets/ofir408/MedConceptsQA © 2024, CC BY.

关键词： Diagnosis

Automatic Multi-Class Non-Functional software Requirements Classification Using Machine Learning Algorithms

学校读者我要写书评

暂无评论

Automatic Multi-Class Non-Functional Software Requirements C...

2024 International Research Conference on Smart Computing and systems engineering, SCSE 2024

作者： Saroth, M.A.F. Wijerathne, P.M.A.K. Kumara, B.T.G.S. Sabaragamuwa University of Sri Lanka Faculty of Computing Department of Computing and Information Systems Sri Lanka Sabaragamuwa University of Sri Lanka Faculty of Computing Department of Software Engineering Sri Lanka

ISBN: (纸本)9798350375688

A successful software development process depends on software requirements. Those requirements are often classified into two categories: functional requirements (FR) and non-functional requirements (NFR). In software development, NFRs play a crucial role, but they are often forgotten by the developers. Therefore, it causes adverse consequences. As a result, an NFR classification method is required to assist software developers in classifying NFR from requirement documents. The majority of research in this area focuses on categorizing requirements as FR or NFR. However, NFR can be divided into more than two categories. As a result, a multi-label categorization strategy was required. This study presented an approach for categorizing NFR based on product, process, and external factors. To categorize the NFR, the authors developed four machine learning-based algorithms entitled Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and K Nearest Neighbor Classifier (KNN) classifier, as well as one deep learning method named Long Short-Term Memory (LSTM) model. Ultimately, the authors examine the models and conclude that the LSTM model which gained an accuracy of 99.69% is appropriate for this type of classification. © 2024 IEEE.

关键词： Long short-term memory

GenKubeSec: LLM-Based Kubernetes Misconfiguration Detection, Localization, Reasoning, and Remediation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Malul, Ehud Meidan, Yair Mimran, Dudu Elovici, Yuval Shabtai, Asaf Department of Software and Information Systems Engineering Ben-Gurion University of The Negev

A key challenge associated with Kubernetes configuration files (KCFs) is that they are often highly complex and error-prone, leading to security vulnerabilities and operational setbacks. Rule-based (RB) tools for KCF misconfiguration detection rely on static rule sets, making them inherently limited and unable to detect newly-discovered misconfigurations. RB tools also suffer from misdetection, since mistakes are likely when coding the detection rules. Recent methods for detecting and remediating KCF misconfigurations are limited in terms of their scalability and detection coverage, or due to the fact that they have high expertise requirements and do not offer automated remediation along with misconfiguration detection. Novel approaches that employ LLMs in their pipeline rely on API-based, general-purpose, and mainly commercial models. Thus, they pose security challenges, have inconsistent classification performance, and can be costly. In this paper, we propose GenKubeSec, a comprehensive and adaptive, LLM-based method, which, in addition to detecting a wide variety of KCF misconfigurations, also identifies the exact location of the misconfigurations and provides detailed reasoning about them, along with suggested remediation. When empirically compared with three industry-standard RB tools, GenKubeSec achieved equivalent precision (0.990 ± 0.020) and superior recall (0.999 ± 0.026). When a random sample of KCFs was examined by a Kubernetes security expert, GenKubeSec’s explanations as to misconfiguration localization, reasoning and remediation were 100% correct, informative and useful. To facilitate further advancements in this domain, we share the unique dataset we collected, a unified misconfiguration index we developed for label standardization, our experimentation code, and GenKubeSec itself as an open-source tool. A video demonstrating our implementation of GenKubeSec can be found here: https://***/hBehYfdR-zM. Copyright © 2024, The Authors. All rights res

关键词： Static analysis

Online Planning for Multi Agent Path Finding in Inaccurate Maps

学校读者我要写书评

暂无评论

Online Planning for Multi Agent Path Finding in Inaccurate M...

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Nir Malka Guy Shani Roni Stern Software and Information Systems Engineering Ben-Gurion University eBay Research

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In multi-agent path finding (MAPF), agents navigate to their target positions without conflict within an environment, typically represented as a graph. Traditionally, the input graph is assumed to be accurate. We investigate MAPF scenarios where the input graph may be inaccurate, containing non-existent edges or missing edges present in the environment. Agents can verify the existence or non-existence of an edge only by moving close to it. To navigate such maps, we propose an online approach where planning and execution are interleaved. As agents gather new information about the environment over time, they replan accordingly. To minimize replanning efforts, we developed methods to identify and replan only for agents affected by observed changes. To scale to larger problems, we defer conflicts resolution expected only in the distant future and adapt single-agent path-finding algorithms to account for map inaccuracies. Experimental results show impressive scalability, solving problems involving over 1000 agents in under 3 minutes.

关键词： Accuracy Navigation Scalability Planning Intelligent robots

CODECLOAK: A METHOD FOR MITIGATING CODE LEAKAGE BY LLM CODE ASSISTANTS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Noah, Amit Finkman Shapira, Avishag Kochva, Eden Bar Maimon, Inbar Mimran, Dudu Elovici, Yuval Shabtai, Asaf Department of Software and Information Systems Engineering Ben-Gurion University of The Negev

LLM-based code assistants are becoming increasingly popular among developers. These tools help developers improve their coding efficiency and reduce errors by providing real-time suggestions based on the developer’s codebase. While beneficial, the use of these tools can inadvertently expose the developer’s proprietary code to the code assistant service provider during the development process. In this work, we propose a method to mitigate the risk of code leakage when using LLM-based code assistants. CodeCloak is a novel deep reinforcement learning agent that manipulates the prompts before sending them to the code assistant service. CodeCloak aims to achieve the following two contradictory goals: (i) minimizing code leakage, while (ii) preserving relevant and useful suggestions for the developer. Our evaluation, employing StarCoder and Code Llama, LLM-based code assistants models, demonstrates CodeCloak’s effectiveness on a diverse set of code repositories of varying sizes, as well as its transferability across different models. We also designed a method for reconstructing the developer’s original codebase from code segments sent to the code assistant service (i.e., prompts) during the development process, to thoroughly analyze code leakage risks and evaluate the effectiveness of CodeCloak under practical development scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Coding errors