Private Graph Data Release using Differential Privacy

A few colleagues and I have just put on arXiv a new survey paper on Private Graph Data Release, which took us nearly 9 months to write. Here’s the abstract: The application of graph analytics to various domains have yielded tremendous societal and economical benefits in recent years. However, the increasingly widespread adoption of graph … More Private Graph Data Release using Differential Privacy

Unsupervised 3D Object Segmentation

One of my PhD students has just released a paper titled Spatially Invariant Unsupervised 3D Object Segmentation Using Graph Neural Networks. Here’s the abstract: In this paper, we tackle the problem of unsupervised 3D object segmentation from a point cloud without RGB information. In particular, we propose a framework, SPAIR3D, to model a point cloud … More Unsupervised 3D Object Segmentation

Towards Fair and Privacy-Preserving Federated Deep Learning Models

My former postdoc Lingjuan Lyu has been working with a few research collaborators on a fair and privacy-preserving federated deep-learning framework and a paper describing the framework has just been published at the IEEE Transactions on Parallel and Distributed Systems. Here’s the paper details: Title: Towards Fair and Privacy-Preserving Federated Deep Models Abstract: The current … More Towards Fair and Privacy-Preserving Federated Deep Learning Models

Distributed Privacy-Preserving Prediction

Another day, another paper, this time by my postdoc Lingjuan Lyu and a few collaborators. Here’s the abstract: In privacy-preserving machine learning, individual parties are reluctant to share their sensitive training data due to privacy concerns. Even the trained model parameters or prediction can pose serious privacy leakage. To address these problems, we demonstrate a … More Distributed Privacy-Preserving Prediction

Accurate and Efficient Privacy-Preserving String Matching

A few ANU colleagues and I have just completed a paper on a suffix-tree-based algorithm for computing the longest common substring of two strings in a privacy-preserving manner. Here’s the abstract: The task of calculating similarities between strings held by different organizations without revealing these strings is an increasingly important problem in areas such as … More Accurate and Efficient Privacy-Preserving String Matching

The Success Formula

The Networks scientist Albert-Laszlo Barabasi’s latest book The Formula: The Science Behind Why People Succeed or Fail is a cracker. His six laws of success summarise more than a decade of research into the science of success, in particular how the social network in which we live and operate, with its many kinds of relationships … More The Success Formula

Legislation as Code

Apparently, everything that has the word Blockchain attached to it is now news-worthy. Or at least that’s how I think this relatively small R&D collaboration between AUSTRAC and Swinburne University of Technology got a mention a couple of days ago in ZDNet, a pretty respectable technology site that has been around forever. Coding the … More Legislation as Code

The Data Quality Trap

There is a lot of work in the data management community that looks at data quality as a first-class problem, capable of being solved largely as an independent problem that can then benefit many downstream systems. There is certainly a lot going for this line of thinking. My own view, drummed into me by a former NASA scientist who I … More The Data Quality Trap