Semantic change detection through large-scale learning. This project aims to develop technologies which understand the content of images before higher-level analysis is performed. This approach is intended to allow more accurate and reliable decisions to be made using automated image analysis than has previously been possible. The project will particularly investigate the detection of change in the contents of an image.
View-based processing of pattern matching queries in large graphs. Graph data exist ubiquitously in modern information systems. Graph pattern matching (GPM) finds parts of the data graph that match a given pattern. It has applications in many areas including knowledge discovery, public health, and crime detection. This project will develop novel techniques for the efficient processing of GPM queries in large graphs.
View and shape invariant modeling of human actions for smart surveillance. This project aims to enable surveillance cameras to interpret videos and detect unexpected activity in real time. Existing surveillance cameras are unable to interpret videos. Because most are not monitored in real time, they play no role in improving security response time. The project plans to develop algorithms to detect actions from any camera viewpoint in continuous videos, a capability that is imperative for smart s ....View and shape invariant modeling of human actions for smart surveillance. This project aims to enable surveillance cameras to interpret videos and detect unexpected activity in real time. Existing surveillance cameras are unable to interpret videos. Because most are not monitored in real time, they play no role in improving security response time. The project plans to develop algorithms to detect actions from any camera viewpoint in continuous videos, a capability that is imperative for smart surveillance yet missing in current techniques. This would improve security and safety response time to events that need immediate attention, such as crimes and medical emergencies, and offer autonomous aids to elderly care, smart homes, child minding, patient monitoring and post-trauma rehabilitation.Read moreRead less
Compression and communication of single and multi-view video based on overlapping motion hint fields. This project explores a new way of communicating motion for video and multi-view (3D) applications, facilitating efficient interactive access to content. Outcomes will include new compression methods that avoid redundant transmission of motion side information, plus client/server technology that leverages metadata from smart surveillance cameras.
Discovery Early Career Researcher Award - Grant ID: DE170100361
Funder
Australian Research Council
Funding Amount
$360,000.00
Summary
Towards reliable and robust machine learning systems. This project aims to protect machine learning systems from adversarial manipulation. Machine learning technologies are used in e-commerce, search, virtual assistants and self-driving cars. However, they are vulnerable to adversarial manipulations which are imperceptible to humans but can cause systems to fail, thereby undermining their usefulness or possibly causing disasters. Less vulnerable machine learning systems are expected to make futu ....Towards reliable and robust machine learning systems. This project aims to protect machine learning systems from adversarial manipulation. Machine learning technologies are used in e-commerce, search, virtual assistants and self-driving cars. However, they are vulnerable to adversarial manipulations which are imperceptible to humans but can cause systems to fail, thereby undermining their usefulness or possibly causing disasters. Less vulnerable machine learning systems are expected to make future autonomous systems, such as self-driving cars and autonomous robots, safer. This project will provide a deeper understanding of how machine learning systems can be made less vulnerable, thereby increasing the safety of future autonomous systems such as self-driving cars and autonomous robots.Read moreRead less
Crowd tracking and visual analytics for rapidly deployable imaging devices. Crowd tracking and visual analytics for rapidly deployable imaging devices. This project aims to develop visual analytics technology that adds machine intelligence to a rapidly deployable time-lapse imaging platform. Such devices can operate on solar and wind power, and be remotely programmed (via a cellular network) to take photos and send them to a server at given times. This project, which focuses on monitoring crowds ....Crowd tracking and visual analytics for rapidly deployable imaging devices. Crowd tracking and visual analytics for rapidly deployable imaging devices. This project aims to develop visual analytics technology that adds machine intelligence to a rapidly deployable time-lapse imaging platform. Such devices can operate on solar and wind power, and be remotely programmed (via a cellular network) to take photos and send them to a server at given times. This project, which focuses on monitoring crowds of objects of interest, is expected to introduce “smart” imaging platforms that could be triggered and shoot high-quality photographs when “events of interest” occur. This project could make Australia both a world leader in video analytics and secure through on-line threat detection, and improve traffic control and agriculture.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE160100584
Funder
Australian Research Council
Funding Amount
$370,000.00
Summary
Secure and Private Machine Learning. This project intends to answer the question: How can machines learn from data when participants behave maliciously for personal gain? Machine learning and statistics are used in many technologies where participants have an incentive to game the system (eg internet ad placement, e-commerce rating systems, credit risk in finance, health analytics and smart utility grids). However, little is known about how well state-of-the-art statistical inference techniques ....Secure and Private Machine Learning. This project intends to answer the question: How can machines learn from data when participants behave maliciously for personal gain? Machine learning and statistics are used in many technologies where participants have an incentive to game the system (eg internet ad placement, e-commerce rating systems, credit risk in finance, health analytics and smart utility grids). However, little is known about how well state-of-the-art statistical inference techniques fare when data is manipulated by a malicious participant. The project's outcomes aim to ensure that statistical analysis is accurate while preserving data privacy, providing theoretical foundations of secure machine learning in adversarial domains. Potential applications range from cybersecurity defences to measures for balancing security and privacy interests.Read moreRead less
A fast and effective automated insider threat detection and prediction system. Threats from insiders directly compromises the security, privacy and integrity of Australian e-commerce, large databases and communication channels. This project will provide an essential step in combating this criminal activity by developing methods to detect such threats and secure the public's information against exposure and identity theft.
Machine learning in adversarial environments. Machine learning underpins the technologies driving the economies of both Silicon Valley and Wall Street, from web search and ad placement, to stock predictions and efforts in fighting cybercrime. This project aims to answer the question: How can machines learn from data when contributors act maliciously for personal gain?