Vicone Corporation

Trend Micro Inc.

Shih-Han Hsu

Yi-Li Cheng

Yao-Tang Chang

Che-Fu Yeh

Ming-Hung Chen

Yu-Min Chang

Jonathan James Oliver

Wen-Kwang Tsao

Peng-Shih Pu

Cheng-Hsin Hsu

Tsung-Fu Lin

I-Ting Lien

Pei-Yin Wu

Wei-Jen Chang

Jui Chang Hsu

Yi-Hong Chu

Pei-Zhong Luo

Chih-Sung Chen

Ming-Lun Li

Shih-Yu Chou

Po-Yuan Teng

Yuan Jiun Tsui

A large language model is trained by inputting a TARA configuration of an ECU of a connected vehicle, an EEA specification, and IDPS rules of the ECU. Software modules are used to extract feature vectors for input to the LLM. The LLM is fine tuned by further inputting later versions of the ECU and data from other ECUs of the vehicle. IDPS rules for another ECU of the vehicle which has no rules or few rules are generated by inputting the TARA configuration of the other ECU into the trained LLM and prompting the LLM to generate rules. The prompt may include instructions to minimize overhead on the other ECU, reduce rules within the vehicle, etc. The generated rules are output from the LLM and stored within the IDPS engine of the other ECU, stored on a computer, transmitted to another vehicle. Rules for two other ECUs may be generated.

Generation of TARA-based IDPS rules utilizing generative artificial intelligence

An object detection system of a vehicle includes a camera and a LIDAR sensor. The camera and the LIDAR sensor sense an environment to generate an image and a point cloud that depict the environment. The image and point cloud are preprocessed to facilitate comparison between the image and the point cloud. Similarity between the image and the point cloud in depicting the environment is determined to detect abnormal sensor data. Abnormal sensor data is further detected based on directional pattern strengths of edges of the image and expanded points of the point cloud. Detected abnormal sensor data in the image and point cloud are filtered to generate a secure image and a secure point cloud, which are provided to a perception engine to detect objects or other features in the environment.

Detection and filtering of abnormal sensor data for object detection in automotive applications

Versions of an application program are evaluated to protect a customer from a supply chain attack. The versions of the application program are executed in to identify behaviors exhibited by the versions of the application program, each of the behaviors including activities that perform computer operations. A behavior change is detected by identifying a behavior that is not common to the versions of the application program.

Protecting customers against supply chain attacks by detecting a behavior change between versions of an application program

A smart home includes Internet of things (IOT) devices that are paired with an IOT gateway. A backend system is in communication with the IOT gateway to receive IOT operating data of the IOT devices. The backend system generates a machine learning model for an IOT device. The machine learning model is consulted with IOT operating data of the IOT device to detect anomalous operating behavior of the IOT device. The machine learning model is updated as more and newer IOT operating data of the IOT device are received by the backend system.

Cybersecurity for a smart home

An email attempting to perpetrate a business email compromise (BEC) attack is detected based on similarity of the email to a known BEC email and on similarity of the email to a user email that would have been sent by the purported sender of the email. Metadata of the email is extracted and input to a BEC machine learning model to find the known BEC email among BEC email samples. The extracted metadata are also input to a personal user machine learning model of the purported sender to generate the user email.

Detection of business email compromise attacks

Growing community of inventors

Taipei, Taiwan

Shih-Han Hsu