A Self-Adaptive Approximated-Gradient-Simulation Method for Black-Box Adversarial Sample Generation
Round 1
Reviewer 1 Report
The paper discusses a novel method of perturbation sample generation for self-adaptive approximated gradient simulation method by which black-box adversarial attacks can be performed. The paper well describes the proposed methodology and correctly evaluates the results in comparison to other most known attack methods.
It is worth mentioning that the domain is a popular research field and that there exist many more methods of attacks published very recently. Therefore it is hard to judge the true value of the proposed research as not all published approaches could be justifiably compared to the method proposed by the paper authors.
From the title I am not well informed whether the method will be about performing or preventing black-bod adversarial attacks. Further, the abstract in the first two sentences gives the impression that DNN adversarial attacks only occur in image classification tasks.
Author Response
Thanks to the editor and reviewers for their detailed and constructive comments which help us to improve the paper. According to the comments, we have made the following revisions. Efforts were also made to correct the mistakes and improve the English of the paper.
Author Response File: Author Response.pdf
Reviewer 2 Report
The researchers used a deep learning model to detect the black box attack from different types of image. authors have done well Major 1- The experiment results part is not explained well, 2 - The quality of the performance of the deep learning model is very poor and not explained. 3- The performance metrics like accuracy , persian, sensitivity are not shown 4. The results of authors model should be compared with recent existing models Minor 1- the article need proofreading 2- Most of reference are old, the reference should be in last three yearsAuthor Response
Thanks to the editor and reviewers for their detailed and constructive comments which help us to improve the paper. According to the comments, we have made the following revisions. Efforts were also made to correct the mistakes and improve the English of the paper.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
Thank you to authorsThe authors were not addressed all comments
1- The results of authors model should be compared with recent existing models
I am not finding responses to this, I am asking with existing work
Author Response
Thanks for your suggestion. According to the suggestions of you, we have added a model experiment for comparison.
Author Response File: Author Response.pdf
Round 3
Reviewer 2 Report
Thank you to authors, but i can't to give acceptance and still my comments not solve
1- I asked authors to use some common evaluation metric like , sensitivity ....etc
2- We can trust to your result if i have seen comparative study with existing research
Author Response
Thanks for your suggestion. According to it, we have added part 4.2.3. Please see the attachment.
Author Response File: Author Response.pdf