# 1. Challenge Description In the current digital information society, the personal authentication technique is an essential tool in many personal and enterprise security systems. Biometrics is an important personal authentication technique based on biological measurements, including physical, physiological, or behavioral characteristics. Compared with existing voice recognition, fingerprint scanning, and facial recognition, EEG-based biometrics has unique advantages (e.g., it is more difficult to be stolen, forged, or damaged, and it must be detected in vivo). Hence, EEG-based biometrics is capable of providing a more secure biometric method for identity recognition. However, at present, EEG-based biometric technique is still in the exploratory stage. Current EEG-based biometric studies are mostly focused on a small number of samples and lack evaluation of multi-session and multi-task EEG recordings, which made the development of EEG-based biometric systems challenging with their uniqueness, permanence, and robustness. At the same time, there is no open EEG-based biometric competition and a suitable database. The lack of a unified test benchmark and platform seriously hinders the development of this field. To this end, we collected the M3CV (A **M**ulti-subject, **M**ulti-session, and **M**ulti-task Database for Investigation of EEG **C**ommonality and **V**ariability) dataset and launched an EEG-based biometric competition. Compared with the existing open dateset, the most challenge 1. Larger population size 2. Multiple sessions of EEG recording 3. Multiple tasks of EEG recording 4. The intruders for the identificationand verification # 2. Task Definition With the 106 subjects, 2 sessions, and 14 types of EEG recoding in M3CV database, we segmented the EEG signal and Sort them out of order. The EEG-based biometric competition was launched by focusing on the problems of personal identification and verification. Based on the enrollment dataset, the participant need to train the prediction model for the biometric system. After the model has been trained, the participant would be asked to complete the following two prediction tasks: - **Identification**: Determine whether a given EEG signal comes from a subject in the Enrollment Set, and further determine the subject ID if he of she is not a intruder. - **Verification**: Determine whether a given EEG signal comes from a certain subject. # 3. Schedule setting | Data | Schedule | | -------- | -------- | | 2022/6/14 | Start the competition registration| | 2022/6/15 | Release datasets for download| | 2022/6/20 | Open the entry of leaderboard A evaluation | | 2022/8/20 | Close the entrance of leaderboard A, and open the entry of leaderboard B to submit materials for review | | 2022/9/25 | Deadline for submission of review materials in leaderboard B | | 2022/9/26 | Announce the ranking and award of the leaderboard B | # 4. Dataset Provider **HUANG Gan** Assistant Professor **LIANG Zhen** Assistant Professor **ZHANG Zhiguo** Professor