CS2125 Paper Review Form - Winter 2019

Reviewer: Yilin Han    

Paper Title: Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Author(s): NAVEED AKHTAR AND AJMAL MIAN

1) Is the paper technically correct?
 [X] Yes
 [ ] Mostly (minor flaws, but mostly solid)
 [ ] No

2) Originality
 [X] Very good (very novel, trailblazing work)
 [ ] Good 
 [ ] Marginal (very incremental)
 [ ] Poor (little or nothing that is new)

3) Technical Depth
 [ ] Very good (comparable to best conference papers)
 [X] Good (comparable to typical conference papers)
 [ ] Marginal depth
 [ ] Little or no depth

4) Impact/Significance
 [ ] Very significant
 [X] Significant
 [ ] Marginal significance.
 [ ] Little or no significance.

5) Presentation
 [ ] Very well written
 [X] Generally well written
 [ ] Readable
 [ ] Needs considerable work
 [ ] Unacceptably bad

6) Overall Rating
 [ ] Strong accept (award quality)
 [X] Accept (high quality - would argue for acceptance)
 [ ] Weak Accept (borderline, but lean towards acceptance)
 [ ] Weak Reject (not sure why this paper was published)


7) Summary of the paper's main contribution and rationale
   for your recommendation. (1-2 paragraphs)

This paper focuses on the adversarial attacks and defenses strategies for readers that have both deep learning and computer vision background. More specifically, the survey covers twelve adversarial attacks that have been observed and also demonstrates fifteen defenses strategies. Besides that, it also displays the main working/researching direction on the adversarial attacks.

I will recommend this paper to those who are trying to explore the field of computer vision and deep learning. It is also a very good paper for people who work in the industry so that they will consider putting the adversarial attacks in their consideration while building robust machine learning models. 

8) List 1-3 strengths of the paper.  (1-2 sentences each,
identified as S1, S2, S3.)

S1: Covered basically all possible adversarial attacks and defenses. A good starting point in the field of adversarial attack.


9) List 1-3 weaknesses of the paper (1-2 sentences each,
identified as W1, W2, W3.)

W1: Not much from the authors themselves.