BTAS-2018 - Special Session On Image And Video Forensics In Biometrics
The advancements in creating high-quality digitally manipulated content of the real world with detailed geometry, surface texture, and material in both static and dynamic environments has posed major problems in various domains. The introduction of highly realistic models such as Face2Face can not only fool the biometric systems but also have a large impact on the digital information channels. Another set of problems include the image manipulation attacks and video manipulation attacks which have proven to defeat the biometric systems. The attack modes have made use of both traditional manipulation approaches and recent adversarial machine learning approaches (eg., GAN). Large-scale projects like DARPA MediFor SAVI and DARPA ODIN BATL have underlined the need to solutions to defend against these attack vectors.
In BTAS-2018, the special session on Image and Video Forensics in Biometrics is organized to evaluate the impact and mitigation measures of such adversarial attacks on biometrics systems. This half-day workshop in conjunction with BTAS-2018, calls for high-quality, previously unpublished works related to approaches and methodologies.
Papers are invited to report on following topics, but not limited to:
- Novel attack mechanisms
- Approaches on evaluating the human perception in detecting such attacks
- Algorithmic advancements in detecting attacks
- Detection and mitigation of adversarial attacks
Topics (not limited to):
- Image manipulation attacks in biometrics verification and identification (e.g., PAD).
- Video manipulation attacks.
- Forensic behavioral biometrics
- Soft Biometrics cues for authenticity verification of biometric data
- Multimedia forensics in biometrics
- Integrity verification and authentication of digital content in biometrics.
- Combination of multimodal decisions for authenticity verification in biometrics.
- Human perception and decisions in biometric data authenticity verification
- Ethical and societal implications of emerging manipulations
- Case studies based on the aforementioned topics
Submissions should conform to the BTAS 2018 proceedings style. Accepted papers from the Special Session will be included in the BTAS Proceedings through IEEE. Papers must be submitted online through the submission systemCMT Submission Site and will be double-blind peer reviewed by at least three reviewers.
## Paper Submission Guidelines
The submitted paper should not be under review in other conferences, workshops, journals. Submitted papers may be checked with a plagiarism detection tool. Simultaneous submission to arxiv is allowed.
Submissions may be up to eight pages in IEEE conference format, excluding references. There is no limit on bibliography pages. Note that papers longer than six pages in the published proceedings will incur a page charge, up to two extra pages (bibliography pages will not incur an extra charge).
Authors can submit one supplementary file. The size should not exceed 100 MB (maximum allowable by CMT) and can be in doc, pdf or zip format.
Papers accepted at the conference must be presented by one of the authors, and at least one of the authors must register before the paper registration deadline. Each author registration applies towards only one paper. If an accepted paper is not registered and/or not presented at the conference, it will be withdrawn from the proceedings and from IEEE Xplore. BTAS 2018 reserves the right to exclude a paper from publication if the paper is not presented (no-show) at the conference.
Authors may not delegate presentation of their paper to a non-author in attendance.
- Authors are required by IEEE to transfer copyrights for any papers placed in Xplore. This is performed at the time final versions are submitted for production. If a paper is withdrawn from the proceedings, copyright will revert to the authors. LaTeX and Microsoft Word templates can be found at:
The review process is double-blind. Please remove author names, affiliations, email addresses, etc. from the paper. Remove personal acknowledgments
When reporting experiments on data collected in your lab, consider stating this as “This experiment was conducted using data acquired in our labs”. Do not state this as “This experiment was conducted using data that was collected in our labs at Mars University” When citing your own work, ensure that the narrative does not divulge your identity.
- Please submit your paper to the Microsoft Conference Management Toolkit at: https://cmt3.research.microsoft.com/BTASSS2018/
Detailed instructions can be found at: https://www.isi.edu/events/btas2018/paper_submission_guidelines
- Workshop: 22nd October, 2018 (Half- day workshop)
- Full Paper Submission: Aug 15th, 2018
- Acceptance Notification: Aug 30th, 2018
- Camera-Ready Paper Due: Sep 15th 2018
Keynote Speaker: To be confirmed