2021

International Workshop

on Safety & Security

of Deep Learning

CALL FOR CONTRIBUTIONS

Deep learning, which is the current representative technology in artificial intelligence, has demonstrated tremendous success in various tasks, such as computer vision, natural language processing, data mining, etc. Unfortunately, deep learning models have also encountered critical safety and security threats in recent years. Due to its implicit vulnerability, deep learning models can be easily affected by the adversarial perturbations and perform abnormally, which may yield serious consequences in certain applications such as autonomous driving, etc. Meanwhile, deep learning models may also be utilized by the malicious attackers to generate forged multimedia content, such as fake images/videos, to deceive people, which may induce trust issues among different people and organizations. In this workshop, we aim to bring more attentions from the researchers in the fields of adversarial attack & defense, forensics, robust deep learning, explainable deep learning, etc., to discuss the recent progresses and future directions for tackling the various safety and security issues of deep learning models.

RELEVANT TOPICS

adversarial attack

adversarial defense

forgery detection

forgery localization

forgery generation

explainable deep learning

interpretable deep learning

robust deep learning


SUBMISSION DETAILS

  • Please submit full technical papers (6-7 pages) in PDF format via CMT online submission system:

    https://cmt3.research.microsoft.com/SSDL2021/

  • Formatting guidelines, LaTeX styles, and Word template:

    https://www.ijcai.org/authors_kit

  • Submitted Papers will be peer-reviewed by the experienced reviewers (2-3 reviewers per paper). The workshop follows a double-blind reviewing process.
  • The workshop proceedings will be published on CEUR-WS.
  • For camera ready submission, please prepare the final submission by using the double-columned template of CEUR-WS (Camera Ready Paper Templates). Please submit all the latex files, including the figures, in a .zip file along with the camera ready pdf file. Please sign and submit the copyright form (Copyright Form) in pdf format as well.
  • For any questions, please send an email to:

    andyguo@buaa.edu.cn

  • IMPORTANT DATES

    May 10, 2021(AOE) May 5, 2021

    Submission Deadline

    May 25, 2021(AOE) May 24, 2021

    May 21, 2021

    Acceptance Notification

    July 10, 2021(AOE)

    Camera Ready Submission

    SCHEDULE(UTC-0)

    The activity schedule is as follows.
    Thursday, August 19, 2021

    14:00~14:05

    Opening Remark

    14:05~15:00

    Invited Talk 1

    15:00~15:55

    Invited Talk 2

    15:55~16:00

    Break

    16:00~18:00

    Oral Session 1 (5 selected papers)
    7: Lip Forgery Video Detection via Multi-phoneme Selection
    16: Self-supervised Deepfake Detection by Discovering Artifact Discrepancies
    2: HCF-Net: Hybrid Coarse-to-Fine Network for Forgery Reconstruction
    3: Exploring the Asynchronous of the Frequency Spectra of GAN-generated Facial Image
    10: Detecting Deepfakes with Multi-metric Loss
    Friday, August 20, 2021

    00:00~00:55

    Invited Talk 3

    00:55~01:50

    Invited Talk 4

    01:50~02:00

    Break

    02:00~04:00

    Oral Session 2 (5 selected papers)
    12: Fingerprint Liveness Detection via Learning Multi-modal Deep Features
    13: Reversible Adversarial Attack based on Reversible Image Transformation
    6: Towards Image Data Hiding via Facial Stego Synthesis with Generative Model
    5: Detection of Adversarial Supports in Few-shot Classifiers Using Self-Similarity and Filtering
    11: Broadly Applicable Targeted Data Sample Omission Attacks

    04:00~04:05

    Closing Remark

    INVITED TALKS

    • Dacheng Tao

      JD Explore Academy

    • Xiangui Kang

      Sun Yat-sen University

    • Siwei Lyu

      University at Buffalo,

      the State University of New York

    • Jun Zhu

      Tsinghua University

    WORKSHOP CHAIRS

    Yuanfang Guo

    (Primary Contact)

    Beihang University

    Bo Li

    University of Illinois Urbana-Champaign

    Xianglong Liu

    Beihang University

    Jiantao Zhou

    University of Macau