[DBWorld] CFP: Frontiers in Big Data - Adversarial Machine Learning for Robust Prediction

"Frontiers in Big Data" has launched a new Research Topic, "Adversarial Mac=
hine Learning for Robust Prediction". Manuscripts will be peer-reviewed and=
, if accepted for publication, will be free to access for all readers, and =
indexed in relevant repositories. =


This is a great opportunity to have your research published in Frontiers in=
 Big Data. Led by Field Chief Editor Huan Liu, it is at the forefront of da=
ta-driven sciences and how acquiring intelligence from information can help=
 address the global challenges of humankind.

Visit the homepage for this Research Topic for a full description of the pr=
oject:
https://www.frontiersin.org/research-topics/20732

The abstract deadline is July 21, 2021.
The submission deadline is September 21, 2021.

More about Journal
---------------------------------------------------------------------------=
---------------------------
Frontiers' Research Topics are collections of peer-reviewed articles around=
 an emerging or cutting-edge theme. As a contributing author, you will bene=
fit from:

  =E2=80=A2  high visibility and the chance to be included in a downloadabl=
e ebook
  =E2=80=A2  rigorous, transparent and fast peer-review for your article
  =E2=80=A2  publication throughout the year, as soon as your article is ac=
cepted
  =E2=80=A2  advanced impact metrics
---------------------------------------------------------------------------=
----------------------------

More about Research Topics
---------------------------------------------------------------------------=
---------------------------
With continued advances in science and technology, digital data have grown =
at an astonishing rate in various domains and forms, such as business, geog=
raphy, health, multimedia, network, text, and web data. Machine learning, a=
 powerful tool for automatically extracting, managing, inferencing, and tra=
nsferring knowledge, has been proven to be extremely useful in understandin=
g the intrinsic nature of real-world big data. Despite achieving remarkable=
 performance, machine learning models, especially deep learning models, suf=
fer from harassment caused by small adversarial perturbations injected by m=
alicious parties and users. There is an immediate and crucial need for theo=
retical and practical techniques to identify the vulnerability of machine l=
earning models and explore the defense mechanism and the certifiable robust=
ness.

The goal of this Research Topic is to present state-of-the-art methodologie=
s build upon an innovative blend of techniques from computer science, mathe=
matics, and statistics, and to greatly expand the reach of adversarial mach=
ine learning from both theoretical and practical points of view, allowing t=
he machine learning models to be deployed in safety and security-critical a=
pplications. This Research Topic will focus on three main research tasks: (=
1) How to develop effective modification 'attack' strategies to tamper with=
 intrinsic characteristics of data by injecting fake information? (2) How t=
o develop defense strategies to offer sufficient protection to machine lear=
ning models against adversarial attacks? (3) How to verify certifiable robu=
stness to adversarial perturbations for a general class of machine learning=
 models? This Research Topic also aims at identifying future challenges and=
 research directions related to adversarial machine learning.

We invite submissions of high-quality manuscripts reporting research in the=
 areas of analyzing, characterizing, understanding, and tackling the vulner=
ability and robustness analysis of various machine learning models under di=
fferent real-world scenarios.

Topics of interest include, but not limited to:
=E2=80=A2 White-box Attack, Gray-box Attack, and Black-box Attack
=E2=80=A2 Poisoning Attack and Evasion Attack
=E2=80=A2 Targeted Attack and Non-targeted Attack
=E2=80=A2 Backdoor Attack
=E2=80=A2 Privacy Attack
=E2=80=A2 Model-agnostic Attack
=E2=80=A2 Attack Imperceivability
=E2=80=A2 Adversarial Defense
=E2=80=A2 Attack Detection
=E2=80=A2 Defensive Distillation
=E2=80=A2 Privacy Defense
=E2=80=A2 Model-agnostic Defense
=E2=80=A2 Certifiable Robustness
=E2=80=A2 Robustness and Regularization
=E2=80=A2 Attack and Defense Transferability
=E2=80=A2 Attack and Defense Automation
=E2=80=A2 Adversarial Attack/Defense on Image/Graph/Text Data

Keywords: Adversarial Machine Learning, Adversarial Attack, Adversarial Def=
ense, Certifiable Robustness, Big Data Analytics
---------------------------------------------------------------------------=
----------------------------

Topic Editors:
 Dr. Yang Zhou, Auburn University, Auburn, United States
 Dr. Neil Gong, Duke University, Durham, United States
 Dr. Ting Wang, Pennsylvania State University, University Park, United Stat=
es
_______________________________________________
Please do not post msgs that are not relevant to the database community at =
large.  Go to www.cs.wisc.edu/dbworld for guidelines and posting forms.
To unsubscribe, go to https://lists.cs.wisc.edu/mailman/listinfo/dbworld