Research highlights
Keeping Your Backdoor Secure
SUTD researchers developed AEGIS, the first and only technique that is able to detect backdoor attacks in robust machine learning models.
Resolving the where and when of social media events
An algorithm that detects events occurring across different time and geographical scales on social media could enable a more timely response to emerging events.
Bluetooth devices proven to be vulnerable to unfixable security vulnerabilities
From having your audio interrupted to your data being wiped out, researchers highlight the security limitation of Bluetooth technology implementations.
Researchers Discover Cyber Vulnerabilities Affecting Bluetooth Based Medical Devices
The Greyhound framework, named after the breed of dogs known for their hunting abilities, was designed to systematically sniff out security lapses in Wi-Fi and Bluetooth enabled devices.
How intelligent is artificial intelligence?
It may often remain unclear, whether the AI’s decision making behavior is truly ‘intelligent’ or whether the procedures are just averagely successful.
Audio Aid Design
Spectral biofeedback has been studied in previous studies as a potential complement to traditional articulation therapy for individuals who have been resistant to traditional articulation therapy.
Scene-based Localisation
The project aims to determine the location of the camera when the query image is taken without GPS assistance.
Crowd-driven Mid-scale Layout Design
This research project proposes a novel approach that that incorporates simulated human crowd flow patterns into the design of middle-scale built environment layouts (e.g., shopping mall, campus, station terminal, theme park).