https://orcid.org/0009-0009-0555-2334
Peer Review History
| Original SubmissionJune 7, 2025 |
|---|
|
-->PONE-D-25-28923-->-->Unsupervised Cross Domain Adaptive Anomaly Detection Network for Internet of Things Traffic-->-->PLOS ONE Dear Dr. Yuan, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.-->--> Please submit your revised manuscript by Dec 19 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript:-->
If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols .. We look forward to receiving your revised manuscript. Kind regards, Elochukwu Ukwandu, PhD Academic Editor PLOS ONE Journal Requirements: When submitting your revision, we need you to address these additional requirements. 1.Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and 2. Please note that PLOS One has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse. 3. Thank you for uploading your study's underlying data set. Unfortunately, the repository you have noted in your Data Availability statement does not qualify as an acceptable data repository according to PLOS's standards. At this time, please upload the minimal data set necessary to replicate your study's findings to a stable, public repository (such as figshare or Dryad) and provide us with the relevant URLs, DOIs, or accession numbers that may be used to access these data. For a list of recommended repositories and additional information on PLOS standards for data deposition, please see https://journals.plos.org/plosone/s/recommended-repositories .. 4. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. Additional Editor Comments: Major revision recommended. [Note: HTML markup is below. Please do not edit.] Reviewer's Responses to Questions -->Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. --> Reviewer #1: Yes Reviewer #2: Yes ********** -->2. Has the statistical analysis been performed appropriately and rigorously? --> Reviewer #1: Yes Reviewer #2: Yes ********** -->3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.-->requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.--> Reviewer #1: Yes Reviewer #2: Yes ********** -->4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.--> Reviewer #1: Yes Reviewer #2: Yes ********** -->5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)--> Reviewer #1: 1. Terminology consistency (“unsupervised” + few-shot tuning) Explicitly state that a small set of normal target samples is used for fine-tuning; align wording across Abstract, Introduction, and Method. 2. Loss details in one place Briefly specify how the domain-adaptation/Wasserstein term is instantiated and list key contrastive-loss hyperparameters (e.g., margin m, balance alpha). 3. Training recipe summary box Add seeds and number of trials to the already-reported learning rate, batch size, and epochs; present them in a compact “Training Setup” box or table for reproducibility. 4. Metrics: add two standard curves Keep Accuracy/MCC/Sensitivity, but add AUC-ROC and AUC-PR for each transfer setting to provide threshold-independent views. 5. Thresholding and decision rule Add one sentence clarifying how detection thresholds are chosen (for example, selected on a validation split using source/normal data). 6. Table 1 caption polish State the number of runs and include 95% confidence intervals (or mean ± std along with the sample count n) to make improvements easy to interpret. 7. Tiny sensitivity check in ablation. Include a brief stability check varying the local/global balance alpha or the contrastive margin; a short text/table in the appendix is sufficient. 8. Figure/notation alignment Ensure symbols in the architecture figure match the equations and add dimensionalities in the caption (latent size, sequence length). 9. Data and code pointers Near the Data Availability statement, add exact preprocessing details (window length, normalization) and, if possible, a link to configs/code. 10. Below articles can be cited: o 10.1109/ICCWorkshops67674.2025.11162261 o 10.1109/VTC2025-Spring65109.2025.11174870 Reviewer #2: - The proposal of combining conditional variational sequence encoding with multi-granularity contrastive learning for unsupervised cross-domain IoT anomaly detection addresses a clear gap in handling domain shifts without requiring labeled target data. However, the paper could strengthen its novelty claim by thoroughly contrasting CDA-ADN with the latest Transformer-based or graph-based anomaly detectors noted in related work. Clarifying how CDA-ADN advances beyond or complements these emerging architectures would enhance the technical contribution. - The description of the conditional variational encoder architecture is somewhat high-level. Including more details such as the exact GRU configuration, latent space dimensionality, and the weighting scheme for the KL divergence term would improve reproducibility. - Similarly, the dynamics of the input-output adaptation layers (latent-guided affine transformations) would benefit from equations or pseudocode to clearly describe how domain alignment is performed. - While the multi-granularity contrastive learning approach is promising, the manuscript should elaborate on the specific loss functions used at local and global levels and how these losses are combined during optimization. This would ensure clarity on how the model balances separating normal from anomalous patterns while preserving domain-invariant features. - The justification for using Wasserstein distance in domain adaptation is briefly mentioned but could be more supported by empirical or theoretical rationale. - The use of two benchmark IoT traffic datasets with no reliance on labeled target anomaly data is appropriate and reflects real-world constraints. However, including additional baselines—especially recent state-of-the-art unsupervised domain adaptation methods—would strengthen empirical comparisons beyond autoencoder and variational autoencoder methods. - The paper mentions improvements in metrics such as Matthews correlation coefficient and sensitivity but should also report specificity and F1-score for a more holistic evaluation. - It would add significant value to include ablation studies that individually assess contributions from: conditional variational encoding, dynamic adaptation layers, and multi-granularity contrastive learning components. This clarity will help justify design choices and pinpoint critical contributors to improved performance. - Additionally, sensitivity analysis on hyperparameters such as the number of target samples in the fine-tuning stage or latent dimension size could provide practical implementation guidance. - The framework assumes availability of “a small subset of normal samples from the target domain” for fine-tuning. It would be helpful to discuss scenarios where even these samples may be scarce or contaminated by anomalies and how CDA-ADN might behave under such conditions or be extended. - Some of the related work citations are old or generic. For example, references [2], [5], and [9] cover classical statistical and deep learning models. Including citations to very recent advances in unsupervised domain adaptation or anomaly detection (last 2 years) would keep the literature review current. - Certain sections (e.g., methodology) could benefit from clearer figures or diagrams depicting the model architecture and training workflow to improve reader comprehension. ********** -->6. PLOS authors have the option to publish the peer review history of their article (what does this mean? ). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy .-->.--> Reviewer #1: No Reviewer #2: No ********** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation. NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications. |
| Revision 1 |
|
-->PONE-D-25-28923R1-->-->Unsupervised Cross Domain Adaptive Anomaly Detection Network for Internet of Things Traffic-->-->PLOS One Dear Dr. Yuan, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.-->--> -->-->Major revision recommended.-->-->-->--> Please submit your revised manuscript by Feb 04 2026 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript:-->
If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols .. We look forward to receiving your revised manuscript. Kind regards, Elochukwu Ukwandu, PhD Academic Editor PLOS One Journal Requirements: If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. Additional Editor Comments (if provided): NB: Tha authors are advised to carefully go through recommended literature and determine suitability before usage as they are not mandatory. [Note: HTML markup is below. Please do not edit.] [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation. NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications. |
| Revision 2 |
|
Unsupervised Cross Domain Adaptive Anomaly Detection Network for Internet of Things Traffic PONE-D-25-28923R2 Dear Dr. Yuan, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support .. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Elochukwu Ukwandu, PhD Academic Editor PLOS One Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions -->Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.--> Reviewer #1: (No Response) Reviewer #2: All comments have been addressed ********** -->2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. --> Reviewer #1: Yes Reviewer #2: Yes ********** -->3. Has the statistical analysis been performed appropriately and rigorously? --> Reviewer #1: Yes Reviewer #2: Yes ********** -->4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.-->requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.--> Reviewer #1: Yes Reviewer #2: Yes ********** -->5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.--> Reviewer #1: Yes Reviewer #2: Yes ********** -->6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)--> Reviewer #1: No further changes are required, all required protocols for the evaluation is been meet in this latest version. Reviewer #2: - The authors have very clearly articulated what "unsupervised" means in the context of their CDA-ADN framework. By explicitly stating that no labeled anomaly samples from the target domain are used, and only a very small number of unlabeled normal samples are employed for lightweight fine-tuning, they successfully clarify the unsupervised nature of their anomaly detection while leveraging minimal target data for adaptation. This distinction is critical and well-addressed in the Abstract, Introduction, and Method sections. - The consolidation of all loss components, including the instantiation of the Wasserstein domain-adaptation term and explicit hyperparameters for contrastive losses (margin 'm', balance 'α', temperature 'τ'), significantly enhances the clarity and reproducibility of the proposed framework. This is a crucial improvement for technical understanding and validation. - The inclusion of a sensitivity analysis for key contrastive learning hyperparameters (balance coefficient 'α' and margin 'm') is commendable. Demonstrating that CDA-ADN maintains high and stable accuracy within a practical range of these parameters provides strong evidence for the model's robustness, a valuable insight for practitioners. - Unifying the notation for latent representations to 'c' throughout the Method section is a minor but important detail that improves readability and reduces potential confusion for readers. - The commitment to release implementation and configuration files on GitHub, along with detailed descriptions of the preprocessing pipeline (z-score normalization, fixed-length windows, stride) in the Experimental Setup, significantly boosts the reproducibility of the work. This transparency is highly valued in scientific research. - Baselines: The decision to extend experimental comparisons to include representative Transformer-based (AT) and graph-based (GDN) baselines addresses a critical point regarding the novelty claim against recent SOTA methods. This allows for a more robust comparison of CDA-ADN's performance. - Additional Dataset: Incorporating the ToN_IoT dataset into the cross-domain evaluation protocol, alongside WUSTL-IIOT-2021 and ACI-IoT-2023, strengthens the empirical validation by demonstrating the framework's robustness and generality across diverse IoT environments. - The update to include Specificity, F1-score, AUC-ROC, and AUC-PR, in addition to Accuracy, MCC, and Sensitivity, provides a much more holistic and robust evaluation, especially crucial given the potential for class imbalance in anomaly detection tasks. The presented Tables 6 and 7 show a clear improvement for CDA-ADN across these diverse metrics. - The expanded ablation study, individually assessing the contributions of the conditional variational encoder, dynamic input–output adaptation layers, and the multi-granularity contrastive learning module, is an excellent addition. This dissection of component contributions provides clear justification for design choices and pinpoints the critical drivers of performance gains, significantly enhancing the technical depth of the paper. - The expanded theoretical and empirical justification for using the Wasserstein-1 distance in domain adaptation, particularly its advantage in providing stable and informative gradients even with limited overlap between distributions, is well-articulated. This strengthens the technical foundation of the chosen approach. ********** -->7. PLOS authors have the option to publish the peer review history of their article (what does this mean? ). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy .-->.--> Reviewer #1: No Reviewer #2: No ********** |
| Formally Accepted |
|
PONE-D-25-28923R2 PLOS One Dear Dr. Yuan, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS One. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset You will receive further instructions from the production team, including instructions on how to review your proof when it is ready. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few days to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. You will receive an invoice from PLOS for your publication fee after your manuscript has reached the completed accept phase. If you receive an email requesting payment before acceptance or for any other service, this may be a phishing scheme. Learn how to identify phishing emails and protect your accounts at https://explore.plos.org/phishing. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Elochukwu Ukwandu Academic Editor PLOS One |
Open letter on the publication of peer review reports
PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.
We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.
Learn more at ASAPbio .