Future Generation Computer Systems-The International Journal of Escience最新文献

筛选
英文 中文
ARTS: An approximate reduced tree and segmentation-based multiplier ARTS:一种近似简化树和基于分割的乘法器
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-22 DOI: 10.1016/j.future.2025.108098
Mahla Salehi Sheikhali Kelayeh , Sahand Divsalar , Shaghayegh Vahdat , Nima TaheriNejad
{"title":"ARTS: An approximate reduced tree and segmentation-based multiplier","authors":"Mahla Salehi Sheikhali Kelayeh ,&nbsp;Sahand Divsalar ,&nbsp;Shaghayegh Vahdat ,&nbsp;Nima TaheriNejad","doi":"10.1016/j.future.2025.108098","DOIUrl":"10.1016/j.future.2025.108098","url":null,"abstract":"<div><div>Due to the increasing use of machine learning applications in daily human life, efficient hardware implementation of these applications has turned into a serious challenge recently. Multipliers are one of the most prevalent, and at the same time expensive (from a hardware perspective), arithmetic units used in such applications. In this paper, a novel approximate multiplier, called ARTS, is designed based on the idea of dividing input operands into different static segments and completing certain steps of the calculation approximately by using simplified reduction trees to sum up the partial products. ARTS manifests significant improvements in hardware characteristics. Namely, 68.6%, 16.5%, and 60% improvements in power, delay, and area are achieved with respect to an exact 8-bit Wallace multiplier, while up to 59.8%, 37.2%, and 52.8% improvements are obtained compared to the other start-of-the-art (SoTA) approximate multipliers. The efficiency of ARTS is assessed in image processing and DNN applications. ARTS shows up to 91.4% and 28.3% better PSNR and 52.4% and 20.5% better SSIM in image multiplication and Sobel edge detection applications, respectively, compared to the other SoTA approximate multipliers. In DNN applications, ARTS exhibits outstanding performance, achieving up to 84.8% higher classification accuracy compared to SoTA approximate designs with similar hardware characteristics. Additionally, when compared to SoTA designs offering comparable accuracy, ARTS achieves this performance with up to 191% lower energy consumption.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108098"},"PeriodicalIF":6.2,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144898692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
High-level multi-platform approaches for scoring phylogenies on CPU and GPU devices 在CPU和GPU设备上评分系统发育的高级多平台方法
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-20 DOI: 10.1016/j.future.2025.108088
Sergio Santander-Jiménez, Miguel A. Vega-Rodríguez
{"title":"High-level multi-platform approaches for scoring phylogenies on CPU and GPU devices","authors":"Sergio Santander-Jiménez,&nbsp;Miguel A. Vega-Rodríguez","doi":"10.1016/j.future.2025.108088","DOIUrl":"10.1016/j.future.2025.108088","url":null,"abstract":"<div><div>Research on parallel computing has promoted significant advances in the solution of different real-world problems. One of the main application domains that have benefited from the exploitation of parallelism is bioinformatics. However, bioinformatics tools are often constrained by the use of low-level platform-specific programming models. This issue limits the spectrum of hardware that can be used to accelerate time-consuming biological workloads, while also affecting programming productivity and code maintenance. To address such limitations, this work investigates high-level multi-platform approaches to parallelize, as a case study, an important task in evolutionary bioinformatics: the evaluation of phylogenetic quality. Particularly, we define parallel designs of the parsimony scoring function for CPU and GPU devices, using three high-level application programming interfaces with multi-platform support: OpenMP, OpenACC, and SYCL. Different optimizations and algorithmic strategies are defined to boost execution according to the characteristics of the tackled parallel tasks. An in-depth experimental evaluation on real-world data reveals the main strengths and areas of improvement for each high-level multi-platform approach, in comparison to lower-level platform-specific alternatives. In addition, the study of single-source performance portability suggests that CPU designs behave better than GPU ones, yet device-oriented optimizations are still needed to pursue a precise exploitation of computational resources.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108088"},"PeriodicalIF":6.2,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Anomaly-aware quantum convolutional neural network for carbon-efficient job arrival rate prediction in cloud computing 云计算中碳效率工作到达率预测的异常感知量子卷积神经网络
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-20 DOI: 10.1016/j.future.2025.108096
Shivani Tripathi , Rajiv Misra , T.N. Singh
{"title":"Anomaly-aware quantum convolutional neural network for carbon-efficient job arrival rate prediction in cloud computing","authors":"Shivani Tripathi ,&nbsp;Rajiv Misra ,&nbsp;T.N. Singh","doi":"10.1016/j.future.2025.108096","DOIUrl":"10.1016/j.future.2025.108096","url":null,"abstract":"<div><div>Cloud computing efficiency hinges on accurately forecasting workload fluctuations, especially for job arrivals where resource allocation must adapt in real-time. In this paper, we present <strong>QAP-Net</strong> (<em>Quantum Arrival Prediction Network</em>), a hybrid model that combines anomaly detection with a quantum + convolutional neural network(CNN) architecture to facilitate carbon-efficient job arrival predictions. The system employs a two-stage pipeline: initially, an Isolation Forest and long short-term memory (LSTM) network identify and reduce the impact of irregular data points in time-series logs. Subsequently, a quantum and CNN-based model called Q-ConvX module uses variational quantum circuits for refined feature extraction, balancing high predictive accuracy with computational efficiency. Our approach specifically addresses key limitations in current forecasting techniques by reducing computational overhead through a quantum-classical hybrid architecture and by improving robustness in dynamic cloud environments via explicit anomaly detection and removal during preprocessing. Beyond these methodological contributions, QAP-Net seamlessly integrates into OpenStack for dynamic auto-scaling, enabling more precise VM provisioning under varying load conditions. Experimental evaluations on Azure VM (2017, 2019) and Google Cluster (2011) datasets(GCD), with aggregation intervals of 10 and 30 minutes, underscore significant resource savings. Precisely, on the Google 2011 dataset, QAP-Net attains an under-provisioning rate of 10.47 % and an over-provisioning rate of 8.93 %, outperforming established methods while also demonstrating measurable reductions in carbon emissions during training and inference. These findings highlight the promise of quantum-classical hybrid solutions in addressing operational efficacy and environmental sustainability within contemporary cloud infrastructures.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108096"},"PeriodicalIF":6.2,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144898452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A hybrid quantum-classical particle-in-cell method for plasma simulations 一种用于等离子体模拟的量子-经典混合细胞内粒子方法
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-19 DOI: 10.1016/j.future.2025.108087
Pratibha Raghupati Hegde , Paolo Marcandelli , Yuanchun He , Luca Pennati , Jeremy J. Williams , Ivy Peng , Stefano Markidis
{"title":"A hybrid quantum-classical particle-in-cell method for plasma simulations","authors":"Pratibha Raghupati Hegde ,&nbsp;Paolo Marcandelli ,&nbsp;Yuanchun He ,&nbsp;Luca Pennati ,&nbsp;Jeremy J. Williams ,&nbsp;Ivy Peng ,&nbsp;Stefano Markidis","doi":"10.1016/j.future.2025.108087","DOIUrl":"10.1016/j.future.2025.108087","url":null,"abstract":"<div><div>We present a hybrid quantum-classical electrostatic Particle-in-Cell (PIC) method, where the electrostatic field Poisson solver is implemented on a quantum computer simulator using a hybrid classical-quantum Neural Network (HNN) using data-driven and physics-informed learning approaches. The HNN is trained on classical PIC simulation results and executed via a PennyLane quantum simulator. The remaining computational steps, including particle motion and field interpolation, are performed on a classical system. To evaluate the accuracy and computational cost of this hybrid approach, we test the hybrid quantum-classical electrostatic PIC against the two-stream instability, a standard benchmark in plasma physics. Our results show that the quantum Poisson solver achieves comparable accuracy to classical methods. It also provides insights into the feasibility of using quantum computing and HNNs for plasma simulations. We also discuss the computational overhead associated with current quantum computer simulators, showing the challenges and potential advantages of hybrid quantum-classical numerical methods.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108087"},"PeriodicalIF":6.2,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Adaptive priority-based edge-centric resource management for the internet of vehicles 基于自适应优先级的车联网边缘中心资源管理
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-19 DOI: 10.1016/j.future.2025.108094
Mohaimin Ehsan , Douglas D. Lieira , Rodolfo I. Meneguette , Robson E. De Grande
{"title":"Adaptive priority-based edge-centric resource management for the internet of vehicles","authors":"Mohaimin Ehsan ,&nbsp;Douglas D. Lieira ,&nbsp;Rodolfo I. Meneguette ,&nbsp;Robson E. De Grande","doi":"10.1016/j.future.2025.108094","DOIUrl":"10.1016/j.future.2025.108094","url":null,"abstract":"<div><div>Vehicle Fog Computing (VFC) enables increased processing capacity and intelligent transportation support services. VFC has become increasingly important for delay-sensitive applications due to its low latency. Vehicles, on the other hand, face difficulties in combining essential services and executing tasks appropriately. Many approaches to pooling idle vehicle resources have been proposed, but few prioritize requests. This proposed approach focuses on hierarchical resource allocation based on priorities, taking into account factors such as deadlines, distances, and mobility issues. Prioritization is achieved through the use of a priority queue, which distributes managed resources based on requests and availability. The hierarchy is implemented synchronously. An iterative ranking mechanism for vehicle resource requests is introduced based on fuzzy membership functions. A Q-learning-based method selects a fog, while the dynamic prioritization technique chooses the vehicle to be served. The technique seeks to reduce the time a service request remains in the system queue, while maintaining good throughput and meeting the criteria for service. QoS. Simulations were performed with realistic mobility models and real maps, including various densities and times, different maps, and varied parameters. In large-scale urban situations, simulated evaluations demonstrate improved response times and overall costs for service requests.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108094"},"PeriodicalIF":6.2,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144895123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Alternative mixed integer linear programming optimization for joint job scheduling and data allocation in grid computing 网格计算联合作业调度和数据分配的可选混合整数线性规划优化
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-18 DOI: 10.1016/j.future.2025.108075
Shengyu Feng , Jaehyung Kim , Yiming Yang , Joseph Boudreau , Tasnuva Chowdhury , Adolfy Hoisie , Raees Khan , Ozgur O. Kilic , Scott Klasky , Tatiana Korchuganova , Paul Nilsson , Verena Ingrid Martinez Outschoorn , David K. Park , Norbert Podhorszki , Yihui Ren , Frédéric Suter , Sairam Sri Vatsavai , Wei Yang , Shinjae Yoo , Tadashi Maeno , Alexei Klimentov
{"title":"Alternative mixed integer linear programming optimization for joint job scheduling and data allocation in grid computing","authors":"Shengyu Feng ,&nbsp;Jaehyung Kim ,&nbsp;Yiming Yang ,&nbsp;Joseph Boudreau ,&nbsp;Tasnuva Chowdhury ,&nbsp;Adolfy Hoisie ,&nbsp;Raees Khan ,&nbsp;Ozgur O. Kilic ,&nbsp;Scott Klasky ,&nbsp;Tatiana Korchuganova ,&nbsp;Paul Nilsson ,&nbsp;Verena Ingrid Martinez Outschoorn ,&nbsp;David K. Park ,&nbsp;Norbert Podhorszki ,&nbsp;Yihui Ren ,&nbsp;Frédéric Suter ,&nbsp;Sairam Sri Vatsavai ,&nbsp;Wei Yang ,&nbsp;Shinjae Yoo ,&nbsp;Tadashi Maeno ,&nbsp;Alexei Klimentov","doi":"10.1016/j.future.2025.108075","DOIUrl":"10.1016/j.future.2025.108075","url":null,"abstract":"<div><div>This paper presents a novel approach to the joint optimization of job scheduling and data allocation in grid computing environments. We formulate this joint optimization problem as a mixed integer quadratically constrained program. To tackle the nonlinearity in the constraint, we alternatively fix a subset of decision variables and optimize the remaining ones via Mixed Integer Linear Programming (MILP). We solve the MILP problem at each iteration via an off-the-shelf MILP solver. Our experimental results show that our method significantly outperforms existing heuristic methods, employing either independent optimization or joint optimization strategies. We have also verified the generalization ability of our method over grid environments with various sizes and its high robustness to the algorithm setting.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108075"},"PeriodicalIF":6.2,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144902984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Distribution-invariance in agent-based spatial simulations 基于智能体的空间模拟中的分布不变性
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-18 DOI: 10.1016/j.future.2025.108054
Mateusz Paciorek, Wojciech Turek
{"title":"Distribution-invariance in agent-based spatial simulations","authors":"Mateusz Paciorek,&nbsp;Wojciech Turek","doi":"10.1016/j.future.2025.108054","DOIUrl":"10.1016/j.future.2025.108054","url":null,"abstract":"<div><div>Large-scale spatial simulations of social beings often exceed the processing capabilities of a single computer. Efficient parallelization and distribution of such simulations is typically based on model partitioning and parallel processing of model parts on many computing nodes. In simulation models which consider mutually exclusive actions of agents, such an approach raises significant problems related to synchronization of the borders between environment partitions processed by different computing nodes. This paper addresses this problem and presents an abstract method for achieving distribution transparency in discrete spatial agent-based simulations. It proposes definitions of distribution-invariance in such simulations and a distribution-invariant simulation algorithm together with formal frames to express the model compliant with the algorithm. A verification of the method in the context of the proposed definitions is presented as well as an analysis of the scalability and applicability of the method.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108054"},"PeriodicalIF":6.2,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144885610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Zero-trust blockchain-enabled framework for scalable and secure IoT networks 零信任区块链框架,支持可扩展和安全的物联网网络
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-18 DOI: 10.1016/j.future.2025.108093
Mikail Mohammed Salim , Minji Kim , Sushil Kumar Singh , Jong Hyuk Park
{"title":"Zero-trust blockchain-enabled framework for scalable and secure IoT networks","authors":"Mikail Mohammed Salim ,&nbsp;Minji Kim ,&nbsp;Sushil Kumar Singh ,&nbsp;Jong Hyuk Park","doi":"10.1016/j.future.2025.108093","DOIUrl":"10.1016/j.future.2025.108093","url":null,"abstract":"<div><div>The rapid expansion of IoT device implementation in environments such as smart cities, factories, and marine industries has introduced significant challenges in security and scalability. Existing blockchain-based IoT security solutions primarily rely on implicit trust to authenticate devices, leaving networks vulnerable to insider attacks, where pre-authenticated devices are compromised to gain unauthorized access. Moreover, the exponential growth in IoT devices exacerbates scalability bottlenecks, overwhelming traditional solutions. In this paper, we propose the Zero-Trust Blockchain-Enabled Framework for Scalable and Secure IoT Networks (ZT-BlocIoT), a comprehensive solution grounded in zero-trust principles, blockchain technology, and AI-based optimization. The framework employs dynamic trusted gateways for continuous device authentication and integrates a Deep Reinforcement Learning (DRL)-driven sharding mechanism to enhance blockchain scalability. The DRL approach dynamically balances shard workloads, minimizes cross-shard transactions, and mitigates adaptive collusion attacks. Evaluation results confirm ZT-BlocIoT’s superior performance, achieving 2500 TPS at 700 nodes, a 14 % increase over competing frameworks. Latency remains at 42 ms, significantly lower than alternatives that reach up to 65 ms. The framework reduces cross-shard transactions, improves node trust evaluation by 41 %, and maintains 85 % throughput even with 20 % malicious nodes, demonstrating strong resilience and security efficiency. These findings validate its AI-driven optimization, enhancing blockchain scalability, security, and real-time adaptability, making it a highly effective solution for secure IoT ecosystems.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108093"},"PeriodicalIF":6.2,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An anti-sandwich mechanism for EVM’s smart contracts EVM智能合约的反夹心机制
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-17 DOI: 10.1016/j.future.2025.108077
Barbara Guidi, Francesco Massellucci, Andrea Michienzi
{"title":"An anti-sandwich mechanism for EVM’s smart contracts","authors":"Barbara Guidi,&nbsp;Francesco Massellucci,&nbsp;Andrea Michienzi","doi":"10.1016/j.future.2025.108077","DOIUrl":"10.1016/j.future.2025.108077","url":null,"abstract":"<div><div>With the advent of blockchain, Decentralised Finance (DeFi) has become an accessible and decentralised method for financial services. One of the most important components of DeFi is the Decentralised Exchanges (DEXs), smart contracts that let users exchange tokens with each other. Trading through DEXs has become crucial in the blockchain ecosystem; however, new malicious activities have begun to spread in parallel. The Maximal Extractable Value (MEV) is becoming pervasive. In this paper, we propose an analysis of the magnitude of MEV activities and a new solution to prevent sandwich attacks after a deep overview of the current anti-MEV approaches. We focused on sandwich attacks because they are the most common MEV attacks (1,330,732 attacks within our 3-year-wide dataset) and cause significant losses to end users ($809,453,320 recorded in our dataset). Our proposed solution prevents sandwich attacks by enhancing token contracts to enforce a cooldown for transferring tokens. Unlike existing approaches, this solution can be easily integrated into any token contract, providing developers with a versatile and customisable MEV solution. Additionally, we extensively evaluate our solution and show that it successfully blocks all sandwich attacks, prove that it does not cause any harm to normal users, and compute that it only introduces a small 3 % gas fee increase.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108077"},"PeriodicalIF":6.2,"publicationDate":"2025-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A formal framework for LLM-assisted automated generation of Zeek signatures from binary artifacts 一个正式的框架,llm辅助从二进制工件自动生成Zeek签名
IF 6.2 2区 计算机科学
Future Generation Computer Systems-The International Journal of Escience Pub Date : 2025-08-16 DOI: 10.1016/j.future.2025.108086
Claudia Greco , Michele Ianni
{"title":"A formal framework for LLM-assisted automated generation of Zeek signatures from binary artifacts","authors":"Claudia Greco ,&nbsp;Michele Ianni","doi":"10.1016/j.future.2025.108086","DOIUrl":"10.1016/j.future.2025.108086","url":null,"abstract":"<div><div>Designing semantically meaningful and operationally effective intrusion detection signatures remains a labor-intensive and expertise-driven task, particularly within the Zeek network monitoring framework. In this paper, we introduce a formalized and modular system for automating Zeek signature generation using Large Language Models (LLMs). Our pipeline begins with static analysis of binary artifacts, extracts salient behavioral features, and transforms them into structured prompts for an LLM tasked with synthesizing Zeek scripts. We provide a rigorous formal framework that defines each stage of this transformation, along with theoretical models for prompt distortion, injection resilience, and sanitization. Furthermore, we explore the adversarial surface exposed by LLMs—introducing a taxonomy of injection attacks, prompt inversion risks, and behavioral feedback loops—and propose mitigations grounded in filtering and robust prompt engineering. Our approach not only accelerates signature creation but also enhances interpretability and adaptability in evolving threat environments. The framework lays the groundwork for future extensions involving dynamic analysis and automated post-validation of generated signatures.</div></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":"175 ","pages":"Article 108086"},"PeriodicalIF":6.2,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144880011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信