Project
This year, students enrolled in this course will
be required to finish a course project. The goals of the course project
include, but not limited to:
-
to study a new security topic. As security
is growing rapidly and new trends are emerging, so
it's important for us to understand the new
frontiers; and
-
to have an opportunity for you to apply what you
have learned in the class about the basic principals of security
to new problems.
Project Topics
Although there are many new emerging security directions, but to
keep us aligned, we will be concentrating on machine learning security
this year. If you really want to choose another topic, you
should discuss with us before the project and get our approval.
There are roughly two directions for machine learning security, we'll
give you some references as starting points, but you are
free to propose your own ideas:
- the security of machine learning systems:
here
is a good starting point;
- to apply machine learning techniques to security
problems: your can start with
this.
To inspire ideas, you might also look at recent machine learning
security publications
from top-tier security conferences, as well as other resources below.
- CCS: ACM
Conference on Computer and Communications Security
- SECURITY:
USENIX Security Symposium
- S & P: IEEE Symposium on
Security and Privacy
- NDSS: The
Network and Distributed System Security Symposium
Collaboration Policy
You should work in a group of no more than 3 students. Working
individually is allowable but not encouraged, not only for
the engineering effort to finish the project is considerable, but also
team collaboration is an important skill in security research (and
all software development) practice.
Important Dates
There will be project proposal, project report and project
presentation. The dates for these items are:
- Project proposal: April 22
- Project report: June 11
- Project presentation: June 18
Project Proposal
The project proposal should be of no more than one page, and should
be written using this template.
Your project proposal should describe:
- What is the problem that you will be investigating? Why is it interesting?
- What reading will you examine to provide context and background?
- What data will you use to conduct the experiment? If you are collecting new data, how will you do it?
-
What method or algorithm are you proposing?
-
If there are existing implementations, will you use them and how?
-
How do you plan to improve or modify such implementations?
-
You don't have to have an exact answer at this point, but you should have a
general sense of how you will approach the problem you are working on.
-
How will you evaluate your results? Qualitatively, what
kind of results do you expect (e.g. plots or figures)?
Quantitatively, what kind of analysis will you use to evaluate
and/or compare your results (e.g. what performance metrics or statistical tests)?
You should submit your proposal before the due date, and you
should give an oral presentation of your proposal.
Project Report
Your should finish and submit a write-up as the project report. The
report should structured like a paper, using this template.
Please make sure to use this template so that the reports are
of the uniform style (fonts, color, spacing, etc..). And we'll post
all the reports online, so that you can learn from each other's
work. If you don't want to your reports posted, please let us know
in advance. Your reports should be written in English (preferred)
or Chinese.
Your project report should be of 4-8 pages, structured like
a research paper. The following
is a recommended structure for your report:
-
Title: what the paper is about;
-
Authors: authors and their contact information;
-
Abstract: Briefly describe the background, the
problem, approach, and key results. Should be no more than 300 words;
-
Introduction: Describe the problem you are working on,
why it's important and challenging, and an overview of your results
(and contribution);
-
Related Work: Discuss published work that relates to
your project. How is your approach similar or different from others?
-
Methods: Discuss your approach for solving the problems
that you set up in the introduction. Why is your approach
the right thing to do? Did you consider alternative
approaches? You should demonstrate that you have applied
ideas and skills built up during the quarter to tackling
your problem of choice. It may be helpful to include figures,
diagrams, or tables to describe your method or compare it with other methods.
-
Experiments and evaluation: Discuss the experiments
that you performed to demonstrate that your approach
solves the problem. The exact experiments will vary
depending on the project, but you might compare with
previously published methods, perform an ablation study
to determine the impact of various components of your
system, experiment with different
architectural choices, use visualization techniques to
gain insight into how your model works, discuss common
failure modes of your model, etc. You should include graphs,
tables, or other figures to illustrate your experimental results.
-
Conclusion: Summarize your key results - what have
you learned? Suggest ideas for future extensions or new applications of your ideas.
Project Presentation
There will be a presentation session. Each group is required to finish a
5-minute presentation for their project. Each group member should
speak during the presentation.
The following is a suggested structure for the presentation. You don't
necessarily have to organize your presentation using these sections
in this order, but that would likely be a good starting point for most projects.
-
Problem Statement: Briefly describe the problem your
group is tackling. Describe the overall motivation,
as well as the input / output of the problem.
-
Technical Challenges: Briefly describe why the problem is
technically challenging.
-
Related Works: Briefly in what ways previous works
have tackled the technical challenges.
-
Your Approach and Results:
Describe your detailed technical approach and innovations.
Describe evaluation results (dataset and metric).
-
Broader Impact:How do you expect the impact of
your work to be? What can others learn from it or how
can they apply it to solve their problems? What are
the limitations of your work? What are areas for future improvements?
|