[visionlist] Call for Papers and Participation of challenges with $100K

[Hang Su]

apologies for multiple posting, please distribute among interested parties

Challenge Registration Deadline: 3/24/2021

Paper Submission Deadline: 5/10/2021

https://aisecure-workshop.github.io/amlcvpr2021/

Dear colleagues,


Workshop on Adversarial Machine Learning in Real-World Computer Vision
Systems and Online Challenges (AML-CV)
<https://aisecure-workshop.github.io/amlcvpr2021/>  will be held virtually
from during CVPR 2021 this year. We will also host a large-scale online
competition
<https://tianchi.aliyun.com/competition/entrance/531847/introduction?lang=en-us>
on adversarial attacks and defenses against real-world systems.



Call for participation in the competition:

the competition includes two tracks.

TRACK 1
<https://tianchi.aliyun.com/competition/entrance/531847/introduction?spm=5176.12281976.0.0.a0884137SbKOuj&lang=en-us>:
White-box Adversarial Attacks on ML Defense Models

TRACK 2:
<https://tianchi.aliyun.com/competition/entrance/531853/introduction?lang=en-us>
Unrestricted Adversarial Attacks on ImageNet

Highlighted Briefings:


   -

   Organizer: Tsinghua University, University of Illinois at
   Urbana-Champaign, Alibaba Security
   -

   Competition Award :Total bonus pool $100,000
   -

   The worlds' first online white-box adversarial attack competition on
   standard benchmark: ImageNet and CIFAR10
   -

   The world's first online no-limit adversarial attack competition with no
   limit on the scale of perturbation


Awards:

Competition Award (Total bonus pool $100,000)

   -

   TOP 1: $20,000
   -

   TOP 2: $10,000
   -

   TOP 3: $5,000
   -

   TOP 4-6: $3,000
   -

   TOP 7-10: $2,000
   -

   Best Paper Award:$1500
   -

   Fancy Idea Awards: Alibaba's 20th Anniversary Limited Medal Box (to the
   creative teams )
   -

   Certificate: Top 10 teams and Fancy Idea Awards
   -

   Green channel: Top 20 teams will win the green channel of Alibaba
   Security Campus Recruitment

Call for Papers:
<https://urldefense.com/v3/__https://dagm-gcpr.de/data/CallforPapers.pdf__;!!DZ3fjg!qBhlFSaZMcRhvpF81fvpILTYNkaWkgNhb2-xn0CRP9Yua8kvTL4vFDWHesKRtHsKW8Y$>
https://cmt3.research.microsoft.com/cvpramlcv2021

This workshop will focus on recent research and future directions for
security problems in real-world machine learning and computer vision
systems. We aim to bring together experts from the computer vision,
security, and robust learning communities in an attempt to highlight recent
work in this area as well as to clarify the foundations of secure machine
learning. We seek to come to a consensus on a rigorous framework to
formulate adversarial machine learning problems in computer vision,
characterize the properties that ensure the security of perceptual models,
and evaluate the consequences under various adversarial models. Finally, we
hope to chart out important directions for future work and cross-community
collaborations, including computer vision, machine learning, security, and
multimedia communities.

Topics of interest include, but are not limited to, the following:

   -

   Real-world attacks against current computer vision models
   -

   Theoretic understanding of adversarial machine learning and certifiable
   robustness
   -

   Vulnerabilities and potential solutions to adversarial machine learning
   in real-world applications, e.g., autonomous driving, 3D object
   recognition, and large-scale image retrieval
   -

   Repeatable experiments adding to the knowledge about adversarial
   examples on image, video, audio, point cloud, and other data
   -

   Real-world data distribution drift and its implications to model
   generalization and robustness
   -

   Detection and defense mechanisms against adversarial examples for
   computer vision systems
   -

   Novel challenges and discoveries in adversarial machine learning for
   computer vision systems
   -

Keynote Speakers:

   -

   Lihi Zelnik (The Technion-Israel Institute of Technology/Alibaba Group)
   -

   Zico Kolter (Carnegie Mellon University)
   -

   Alina Oprea (Northeastern University)
   -

   Lujo Bauer (Carnegie Mellon University)
   -

   Nicholas Papernot (University of Toronto)
   -

   Ding Zhao (Carnegie Mellon University)
   -

   Trevor Darrell (University of California, Berkeley)
   -

   Una-May O’Reilly (Massachusetts Institute of Technology)


Important Dates:

Paper Submission:

   -

   Paper Submission Deadline: 5/10/2021
   -

   Decisions to Authors: 6/1/2021
   -

   Camera Ready Deadline: 6/12/2021

Competition:

   -

   Registration Opens: 1/15/2021
   -

   Submission Starts: 1/22/2021
   -

   Registration Deadline: 3/24/2021
   -

   Submission Deadline: 3/31/2021
   -

Organizers:

   -

   Dawn Song (University of California, Berkeley)
   -

   Bo Li (University of Illinois at Urbana-Champaign)
   -

   Jun Zhu (Tsinghua University)
   -

   Hang Su (Tsinghua University)
   -

   Hui Xue (Alibaba Group)
   -

   Yuan He (Alibaba Group)

--

Contact: lbo at illinois.edu

Website:
<https://urldefense.com/v3/__https://twitter.com/dagmgcpr__;!!DZ3fjg!qBhlFSaZMcRhvpF81fvpILTYNkaWkgNhb2-xn0CRP9Yua8kvTL4vFDWHesKRjrDXUDA$>Adversarial
Machine Learning in Real-World Computer Vision Systems and Online
Challenges (AML-CV) | Workshop at CVPR 2021
<https://aisecure-workshop.github.io/amlcvpr2021/>

CompetitonTrack1:
https://tianchi.aliyun.com/competition/entrance/531847/introduction?lang=en-us


CompetitonTrack2:
https://tianchi.aliyun.com/competition/entrance/531853/introduction?lang=en-us

Slack：
https://join.slack.com/t/ai-challenge-group/shared_invite/zt-mvjb1d8y-tvSbCA93snLX4j8L99Ed3A


-- 
Hang (Steven) Su, Ph. D
Department of Computer Science and Technology
Tsinghua University, Beijing, China, 100084
Tel: 138-1066-7245
E-mail: suhangss at mail.tsinghua.edu.cn
Personal website: http://www.suhangss.me/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20210302/e4dedd87/attachment-0001.html>