Internet of Things and Cyber-Physical Systems最新文献_第2页

Securing LLM agents: From prompt sanitization to autonomous red teaming and beyond 保护LLM代理：从及时消毒到自主红队等

Internet of Things and Cyber-Physical Systems Pub Date : 2025-01-01 Epub Date: 2026-03-11 DOI: 10.1016/j.iotcps.2026.03.001

Mohamed Amine Ferrag , Abderrahmane Lakas , Norbert Tihanyi , Merouane Debbah

{"title":"Securing LLM agents: From prompt sanitization to autonomous red teaming and beyond","authors":"Mohamed Amine Ferrag , Abderrahmane Lakas , Norbert Tihanyi , Merouane Debbah","doi":"10.1016/j.iotcps.2026.03.001","DOIUrl":"10.1016/j.iotcps.2026.03.001","url":null,"abstract":"<div><div>Large Language Models (LLMs) are rapidly transitioning from standalone conversational systems to autonomous agents that reason, plan, and interact with external tools. While this shift enables powerful applications in domains such as healthcare, finance, law, and software engineering, it also introduces new security and safety risks. Attacks such as prompt injection, jailbreak exploits, backdoor triggers, and multimodal adversarial inputs expose vulnerabilities not only at the model level but also across the broader agentic workflow. Existing defenses—ranging from input filtering and alignment reinforcement to runtime monitoring—remain fragmented and often fail to anticipate adaptive adversaries. Meanwhile, red teaming has emerged as a critical methodology for stress-testing these systems; however, current efforts lack standardization, comprehensive coverage across modalities, and integration with agent-specific contexts. This paper provides the first comprehensive survey of LLM agent security, synthesizing research on attack strategies, red teaming frameworks, evaluation suites, and defense mechanisms. We categorize automated and agentic red teaming approaches, highlight domain-specific vulnerabilities in code, web, and multimodal agents, and analyze defense strategies spanning prompt-level, decoding-time, runtime, backdoor, privacy-preserving, and multi-agent safeguards. Building on this synthesis, we outline key open challenges and future research directions, including the need for scalable defenses, standardized benchmarks, robustness against adaptive attacks, explainability, and secure integration of multi-agent workflows. Our findings aim to guide both researchers and practitioners in advancing robust, trustworthy, and resilient LLM-powered agents for safety-critical applications.</div></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"5 ","pages":"Pages 185-209"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147537858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive privacy-preserving federated learning for robust IoT systems: A defense against data poisoning attacks 稳健物联网系统的自适应隐私保护联邦学习：防御数据中毒攻击

Internet of Things and Cyber-Physical Systems Pub Date : 2025-01-01 Epub Date: 2026-03-24 DOI: 10.1016/j.iotcps.2026.03.006

Sajjad Khan , Davor Svetinovic

引用次数: 0

Non-work conserving dynamic scheduling of moldable gang tasks on multicore systems 多核系统上可成型团伙任务的非工作保护动态调度

Internet of Things and Cyber-Physical Systems Pub Date : 2024-03-01 DOI: 10.1016/j.iotcps.2024.03.001

Tomoki Shimizu, Hiroki Nishikawa, Xiangbo Kong, Hiroyuki Tomiyama

引用次数: 0

Constructing immersive toy trial experience in mobile augmented reality 在移动增强现实技术中构建身临其境的玩具试用体验

Internet of Things and Cyber-Physical Systems Pub Date : 2024-02-01 DOI: 10.1016/j.iotcps.2024.02.001

Lingxin Yu, Jiacheng Zhang, Xinyue Wang, Siru Chen, Xuehao Qin, Zhifei Ding, Jiahao Han

引用次数: 0

Multi-objective optimization algorithms for intrusion detection in IoT networks: A systematic review 物联网网络入侵检测的多目标优化算法：系统综述

Internet of Things and Cyber-Physical Systems Pub Date : 2024-02-01 DOI: 10.1016/j.iotcps.2024.01.003

Shubhkirti Sharma, Vijay Kumar, K. Dutta

引用次数: 0

MalAware: A tabletop exercise for malware security awareness education and incident response training 恶意软件：恶意软件安全意识教育和事件响应培训桌面演练

Internet of Things and Cyber-Physical Systems Pub Date : 2024-01-01 Epub Date: 2024-03-13 DOI: 10.1016/j.iotcps.2024.02.003

Giddeon Angafor , Iryna Yevseyeva , Leandros Maglaras

{"title":"MalAware: A tabletop exercise for malware security awareness education and incident response training","authors":"Giddeon Angafor , Iryna Yevseyeva , Leandros Maglaras","doi":"10.1016/j.iotcps.2024.02.003","DOIUrl":"https://doi.org/10.1016/j.iotcps.2024.02.003","url":null,"abstract":"<div><p>Advancements in technology, including the Internet of Things (IoT) revolution, have enabled individuals and businesses to use systems and devices that connect, exchange data, and provide real-time information from far and near. Despite that, this interconnectivity and data sharing between systems and devices over the internet poses security and privacy risks as threat actors can intercept, steal, and use owners’ data for nefarious purposes. This paper discusses ’MalAware’, a ‘Malware Awareness Education’ and incident response (IR) scenario-based tabletop exercise and card game for malware threat mitigation training. It introduces the importance of incident management, highlights the dangers posed by malware for connected systems, and outlines the role of tabletop games and exercises in helping businesses mature their malware incident response capabilities. The study discusses the design of MalAware and summarises the results of 2 pilots undertaken to assess the concept, maintaining that the results highlighted the value of ‘MalAware’ as an essential tool to help students and staff master how to mitigate security threats caused by malware. It argues that MalAware can assist businesses in their IR preparedness endeavors, enabling incident management teams to review plans and processes to ensure they are fit for purpose. It enables staff to leverage scenario-based and simulated security breach examples, including role-play, to establish appropriate malware defences. MalAware’s practical hands-on exercises can assist trainees in gaining essential malware and other threat mitigation skills, helping to protect the security and privacy of IoTs.</p></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"4 ","pages":"Pages 280-292"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667345224000063/pdfft?md5=61feca14037fa00f21581df14b5c4571&pid=1-s2.0-S2667345224000063-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140180017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DBSCAN inspired task scheduling algorithm for cloud infrastructure 基于DBSCAN的云基础设施任务调度算法

Internet of Things and Cyber-Physical Systems Pub Date : 2024-01-01 Epub Date: 2023-07-14 DOI: 10.1016/j.iotcps.2023.07.001

S.M.F D Syed Mustapha , Punit Gupta

引用次数: 0

Transformative effects of ChatGPT on modern education: Emerging Era of AI Chatbots ChatGPT对现代教育的变革影响:人工智能聊天机器人的新兴时代

Internet of Things and Cyber-Physical Systems Pub Date : 2024-01-01 Epub Date: 2023-06-19 DOI: 10.1016/j.iotcps.2023.06.002

Sukhpal Singh Gill , Minxian Xu , Panos Patros , Huaming Wu , Rupinder Kaur , Kamalpreet Kaur , Stephanie Fuller , Manmeet Singh , Priyansh Arora , Ajith Kumar Parlikad , Vlado Stankovski , Ajith Abraham , Soumya K. Ghosh , Hanan Lutfiyya , Salil S. Kanhere , Rami Bahsoon , Omer Rana , Schahram Dustdar , Rizos Sakellariou , Steve Uhlig , Rajkumar Buyya

{"title":"Transformative effects of ChatGPT on modern education: Emerging Era of AI Chatbots","authors":"Sukhpal Singh Gill , Minxian Xu , Panos Patros , Huaming Wu , Rupinder Kaur , Kamalpreet Kaur , Stephanie Fuller , Manmeet Singh , Priyansh Arora , Ajith Kumar Parlikad , Vlado Stankovski , Ajith Abraham , Soumya K. Ghosh , Hanan Lutfiyya , Salil S. Kanhere , Rami Bahsoon , Omer Rana , Schahram Dustdar , Rizos Sakellariou , Steve Uhlig , Rajkumar Buyya","doi":"10.1016/j.iotcps.2023.06.002","DOIUrl":"https://doi.org/10.1016/j.iotcps.2023.06.002","url":null,"abstract":"<div><p>ChatGPT, an AI-based chatbot, offers coherent and useful replies based on analysis of large volumes of data. In this article, leading academics, scientists, distinguish researchers and engineers discuss the transformative effects of ChatGPT on modern education. This research discusses ChatGPT capabilities and its use in the education sector, identifies potential concerns and challenges. Our preliminary evaluation shows that ChatGPT perform differently in different subject areas including finance, coding, maths, and general public queries. While ChatGPT has the ability to help educators by creating instructional content, offering suggestions and acting as an online educator to learners by answering questions, transforming education through smartphones and IoT gadgets, and promoting group work, there are clear drawbacks in its use, such as the possibility of producing inaccurate or false data and circumventing duplicate content (plagiarism) detectors where originality is essential. The often reported “hallucinations” within GenerativeAI in general, and also relevant for ChatGPT, can render its use of limited benefit where accuracy is essential. What ChatGPT lacks is a stochastic measure to help provide sincere and sensitive communication with its users. Academic regulations and evaluation practices used in educational institutions need to be updated, should ChatGPT be used as a tool in education. To address the transformative effects of ChatGPT on the learning environment, educating teachers and students alike about its capabilities and limitations will be crucial.</p></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"4 ","pages":"Pages 19-23"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49884566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 19

IoT-enhanced smart road infrastructure systems for comprehensive real-time monitoring 用于全面实时监控的物联网增强型智能道路基础设施系统

Internet of Things and Cyber-Physical Systems Pub Date : 2024-01-01 Epub Date: 2024-02-05 DOI: 10.1016/j.iotcps.2024.01.002

Zhoujing Ye , Ya Wei , Songli Yang , Pengpeng Li , Fei Yang , Biyu Yang , Linbing Wang

{"title":"IoT-enhanced smart road infrastructure systems for comprehensive real-time monitoring","authors":"Zhoujing Ye , Ya Wei , Songli Yang , Pengpeng Li , Fei Yang , Biyu Yang , Linbing Wang","doi":"10.1016/j.iotcps.2024.01.002","DOIUrl":"https://doi.org/10.1016/j.iotcps.2024.01.002","url":null,"abstract":"<div><p>With the rapid advancement of Internet of Things (IoT) technology, its applications in road infrastructure have garnered attention. However, challenges persist when applying IoT to road infrastructure monitoring, including insufficient durability of front-end sensors, pavement damage due to sensor embedding, and the redundancy of a vast amount of real-time data, hindering the long-term real-time monitoring of pavements. To address these challenges, this study developed a self-powered distributed intelligent pavement monitoring system based on IoT, encompassing a sensor network, cloud platform, communication network, and power supply system. Considering the specific characteristics of slipform paving for cement concrete pavements, an integrated paving process was proposed, merging embedded sensors with pavement material structures. Through on-site engineering monitoring, the system actively collects and analyzes various data types such as system energy consumption, temperature and humidity, environmental noise, wind speed and direction, and pavement structural vibrations, providing data support for pavement design, maintenance, and vehicle-road synergy applications. Future efforts will continue to promote the application of IoT technology in digital road maintenance, traffic safety, and optimized pavement material structure design.</p></div>","PeriodicalId":100724,"journal":{"name":"Internet of Things and Cyber-Physical Systems","volume":"4 ","pages":"Pages 235-249"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667345224000026/pdfft?md5=e2593131eb914f50ce726004b9037d6b&pid=1-s2.0-S2667345224000026-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139718721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advancing civil infrastructure assessment through robotic fleets 通过机器人车队推进民用基础设施评估

Internet of Things and Cyber-Physical Systems Pub Date : 2024-01-01 Epub Date: 2023-10-21 DOI: 10.1016/j.iotcps.2023.10.003

Kay Smarsly, Kosmas Dragos

引用次数: 0