Defense against adversarial attacks on deep learning in computer vision. Computer vision applications rely heavily on deep learning, which is highly vulnerable to being fooled by adding subtle perturbations to object/image textures that are imperceptible to humans. This project aims to develop defense mechanisms to detect and remove adversarial patterns from the input images. The project expects to advance knowledge in understanding the vulnerabilities of deep learning, and to design deep learni ....Defense against adversarial attacks on deep learning in computer vision. Computer vision applications rely heavily on deep learning, which is highly vulnerable to being fooled by adding subtle perturbations to object/image textures that are imperceptible to humans. This project aims to develop defense mechanisms to detect and remove adversarial patterns from the input images. The project expects to advance knowledge in understanding the vulnerabilities of deep learning, and to design deep learning architectures that are inherently robust. The outcomes of this project will increase the security and reliability of computer vision by detecting, reporting and nullifying such attacks and will benefit the general public and industry on many fronts.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE130100156
Funder
Australian Research Council
Funding Amount
$210,000.00
Summary
Computational infrastructure for machine learning in computer vision. The many trillions of images stored on computers around the world, including more than 100 billion on Facebook alone, represent exactly the information needed to develop artificial vision. All we need do is extract it. This project will develop the computational infrastructure required to allow Australian researchers to achieve this goal.
Monitoring intuitive expertise in the context of airport security screening. During airport security screening and processing, confusion and error are greatest when systems or contexts are unfamiliar. Poorly designed systems compromise the interactions of airport security personnel and decrease their ability to promptly and accurately respond to situations. This project aims to deliver a suite of automated methods to monitor security operator knowledge and engagement, to assess the real-time sec ....Monitoring intuitive expertise in the context of airport security screening. During airport security screening and processing, confusion and error are greatest when systems or contexts are unfamiliar. Poorly designed systems compromise the interactions of airport security personnel and decrease their ability to promptly and accurately respond to situations. This project aims to deliver a suite of automated methods to monitor security operator knowledge and engagement, to assess the real-time security screening context, and to detect unusual passenger behaviour at the screening check-point. This monitoring aims to provide new knowledge and techniques to enhance security operator performance, refine the screening process, improve passenger experience and, most critically, ensure safety at Australian airports.Read moreRead less
A theoretical framework for practical partial fingerprint identification. Fingerprints captured from a crime scene are often partial and poor quality which makes it difficult to identify the criminal suspects from large databases. This project will find mathematical models which can estimate the missing information located in the blank areas of a partial fingerprint and effectively identify it.
A three dimensional video-based vision system for future robots. With the recent introduction of new three dimensional (3D) video sensors, opportunities for the development of advanced 3D vision systems for robots working in dynamic environments are now becoming possible. A real-time visual robotic system will be developed to substantially reduce the expensive costs associated with elder's health and home care expenses.