The boring and repetitive task of monitoring video feeds makes real-time anomaly detection tasks difficult for humans. Hence, crimes are usually detected hours or days after the occurrence. To mitigate this, the research community proposes the use of a deep learning-based anomaly detection model (ADM) for automating the monitoring process.
This is the dataset provided and collected while "Car Hacking: Attack & Defense Challenge" in 2020. We are the main organizer of the competition along with Culture Makers and Korea Internet & Security Agency. We are very proud of releasing these valuable datasets for all security researchers for free.
The competition aimed to develop attack and detection techniques of Controller Area Network (CAN), a widely used standard of in-vehicle network. The target vehicle of competition was Hyundai Avante CN7.
|Round||Type||Description||# Normal||# Attack||# Rows|
|Preliminary||Training||Normal and four types of attacks dataset with class||3,372,743||299,408||3,672,151|
|Submission||Normal and four types of attacks dataset with class|
(during the competition, without class)
|Final||Submission||Normal and five attacks (4 spoofings, 1 fuzzing) dataset with class|
(during the competition, without class)
Normal: Normal traffic in CAN bus.
Attack: Attack traffic injected. Four types of attacks are included -- Flooding, Spoofing, Replay, Fuzzing.
Flooding: Flooding attack aims to consume CAN bus bandwidth by sending a massive number of messages.
Spoofing: CAN messages are injected to control certain desired function.
Replay: Replay attack is to extract normal traffic at a specific time and replay (inject) it into the CAN bus.
Fuzzing: Random messages are injected to cause unexpected behavior of the vehicle.
This work was supported by Institute for Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-00866, Challenges for next generation security R&D).
Protein molecules are inherently dynamic and modulate their interactions with different molecular partners by accessing different tertiary structures under physiological conditions.Elucidating such structures remains challenging. Current momentum in deep learning and the powerful performance of generative adversarial networks (GANs) in complex domains, such as computer vision, inspires us to investigate GANs on their ability to generate physically-realistic protein tertiary structures.
Generated data, input data and saved models for the publication
Taseef Rahman, Yuanqi Du, Liang Zhao, and Amarda Shehu. Generative Adversarial Learning of Protein Tertiary Structures. Molecules, 2021.
is made available. Instructions accompany the data in a ReadMe.txt in each folder respectively for the ease of use.
This data set is the result of model test trained on the basis of the Stanford earthquake dataset (stead): a global data set of seismic signals for AI, which can effectively get the seismic signal and the arrival time of seismic phase from the image, so as to prove the effectiveness of this model
A Multi-Agent Approach for Personalized Hypertension Risk Prediction
Please Refer to the paper for further instructions. Our paper is currently under review
Trajectory generation for robotic pick-and-place task using nested double-memory deep deterministic policy gradient.
YonseiStressImageDatabase is a database built for image-based stress recognition research. We designed an experimental scenario consisting of steps that cause or do not cause stress; Native Language Script Reading, Native Language Interview, Non-native Language Script Reading, Non-native Language Interview. And during the experiment, the subjects were photographed with Kinect v2. We cannot disclose the original image due to privacy issues, so we release feature maps obtained by passing through the network.
- Subject Number (01~50)
- Data acquisition phase
(Native Language Script Reading, Native Language Interview, Non-native Language Script Reading, Non-native Language Interview)
- Data (*.npy, the filename is set to the time the data was acquired; YYYYMMDD_hhmmss_ms)
In the case 'Non-native_Language_Interview' data of subject 26, it was not acquired due to equipment problems.
If you use YonseiStressImageDatabase in a scientific publication, we would appreciate references to the following paper:
Copyright © 2019 AI Hub, Inc., https://aihub.or.kr/
AI data provided by AI Hub was built as part of a business National Information Society Agency's 'Intelligent information industry infrastructure construction project' in Korea, and the ownership of this database belongs to National Information Society Agency.
Specialized field AI data was built for artificial intelligence technology development and prototype production and can be used for research purposes in various fields such as intelligent services and chatbots.