All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Since the comments have been addressed, we are happy to inform you that your manuscript has been accepted for the publication.
[# PeerJ Staff Note - this decision was reviewed and approved by Vicente Alarcon-Aquino, a 'PeerJ Computer Science' Section Editor covering this Section #]
The changes made are sufficient.
The changes made are sufficient.
The changes made are sufficient.
The revised manuscript can be accepted as presented.
The revised manuscript can be accepted as presented.
The revised manuscript can be accepted as presented.
The reviewers have pointed out that important parts are missing. More details are still needed.
[# PeerJ Staff Note: This is a resubmission of a submission which previously received an "open rejection" decision. R1 and R2 were 2 of the original reviewers on that earlier submission #]
You presented a method for detecting unknown malware families using the Zero Shot learning method. However, I could not see a class belonging to zero-day attacks in the dataset. How did you detect zero-day attacks or how did you determine that they could be detected?
It is insufficient to compare your method with the ResNet-34 architecture. There are many CNN architectures. You should also compare it with architectures with different structures.
Has an ablation study been done? If you can obtain an accuracy and fscore, you can also add roc curves.
As pointed out below, the authors have not fully addressed the requested revisions.
- Why does the validation curve in the loss curve shown in Figure 13 end at the 100th epoch? This loss curve is not correct for proper training.
- AUC Metric also can be provided.
- Providing the confusion matrix would also help in better understanding the model's performance.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.