Oct 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23109457. Abstract: The abstract contains wordings that does not clearly described the methodology and the major knowledge gap. A review abstract should preferably follow a structured logic: Background → Objective → Methods → Results/findings → Conclusions. Introduction: The introduction has repetitions on it Literature review and Methods: The manuscript lacks a clearly defined review methodology. The article calls itself a "Comprehensive Review," but there is no adequate description of: databases searched; search dates; search strings; inclusion criteria; exclusion criteria; screening process; number of records identified; duplicate removal; full-text assessment; final number of studies included; quality/risk-of-bias assessment; method used for synthesizing the evidence. Discussion: The review should have a clear description of why cloud/IOT security matters and why convectional IDS approaches are insufficient. General Comment: Please take note of the grammar usage. For a review claiming comprehensiveness, this is a substantial methodological deficiency. The authors should either: A. Convert it into a systematic/scoping review, with an appropriate methodology and reporting framework such as PRISMA 2020 where applicable, or B. Clearly identify it as a narrative review and explain the literature-search and selection approach sufficiently to establish transparency. At present, the word "comprehensive" is not adequately supported by the methodology. The manuscript does not adequately distinguish cloud IDS from IoT IDS The title emphasizes: "Cloud and IoT Infrastructures" but much of the manuscript treats them together without sufficiently explaining their different security and architectural requirements. The authors should develop a stronger comparative analysis. The datasets require much more critical discussion. The manuscript mentions datasets such as: KDD99; NSL-KDD; CSE-CIC-IDS2018; RedIRIS. However, it does not critically discuss their suitability such as the security concepts. A comprehensive review should include a dedicated table containing: Dataset | Year | Environment | Attack types | Number of features | Limitations | Cloud/IoT relevance Tables need improvement: Tables should contain more analytical information rather than merely definitions. In particular, Table 3 should become a major synthesis table. Competing interests The authors declare that they have no competing interests. Use of Artificial Intelligence (AI) The authors declare that they did not use generative AI to come up with new ideas for their review.
The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.
Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson· EUROMICRO Conference on Soft...· 64 citations· ⚡6
The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.
Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al.· arXiv.org· 62 citations· ⚡3
A comprehensive overview of how enhanced sampling methods are reshaping the field, with a particular focus on the data-driven construction of collective variables, is provided.
Kai Zhu, Enrico Trizio, Jintu Zhang et al.· Chemical Reviews· 58 citations
The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.
Zheying Zhang, M. Rayhan, Tomas Herda et al.· International Conference on...· 48 citations· ⚡4
This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.
Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al.· arXiv.org· 44 citations· ⚡2
The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.
Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al.· arXiv.org· 41 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.