Toby is a Professor whose research is focused on the problem of how to build highly secure computing systems cost-effectively. Prior to joining Melbourne in May 2016, he was employed in the Software Systems Research Group of NICTA (now Data61), and was a Conjoint Senior Lecturer in the school of Computer Science and Engineering of UNSW.
Security research at the University of Melbourne.
We work across cryptography, formal methods, software and systems security, privacy, and trustworthy machine learning.
People
Teaching and research faculty
News
Recent updates from the group
Congratulations to Neil Marchant on his ICLR 2026 paper "On the Bayes Inconsistency of Disagreement Discrepancy Surrogates"
Presented at ICLR 2026, this work gives new theory for disagreement discrepancy surrogates under distribution shift and introduces a provably consistent alternative.
Congratulations to Neil Marchant on his NeurIPS 2025 paper "Adaptive Data Analysis for Growing Data"
This NeurIPS 2025 paper studies adaptive data analysis in settings where the underlying dataset grows over time.
AdaptDel presented at NeurIPS 2025
AdaptDel was presented at NeurIPS 2025 and develops certified robustness guarantees for sequence models under edit-distance perturbations.
Congratulations to Xingliang Yuan on his USENIX Security 2025 paper "V-ORAM: A Versatile and Adaptive ORAM Framework with Service Transformation for Dynamic Workloads"
V-ORAM appeared at the 34th USENIX Security Symposium and proposes an adaptive ORAM framework for changing workloads.
Congratulations to Xingliang Yuan on his USENIX Security 2025 paper "THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models"
THEMIS was presented at the 34th USENIX Security Symposium in Seattle and studies practical protection mechanisms for deployed on-device deep learning models.
Trailblazer presented at FUZZING 2025
Presented at FUZZING 2025, co-located with ISSTA 2025, Trailblazer introduces an end-to-end workflow for testing web APIs even when no machine-readable specification is available.
Congratulations to Shaanan Cohney on his IEEE S&P 2025 paper "It's been lovely watching you": Institutional Decision-Making on Online Proctoring Software
The paper, coauthored with collaborators at George Washington University and Barnard College, was accepted to the 46th IEEE Symposium on Security and Privacy.
Writing
Public writing and commentary
What the Moltbook experiment is teaching us about AI
An experimental social media platform where only AI bots can post offers a concrete way to study model behaviour, coordination, and safety.
Submission to Parliament on Harmful Digital Communications
A parliamentary submission on harmful digital communications and platform governance, with Shaanan as primary author.
Collaborative Research, Not Competitive Research
A conversation about how the group reads papers, develops ideas, and writes stronger research.
Submission to Senate Inquiry: Online Safety Amendment (Social Media Minimum Age) Bill 2024
A group submission on the proposed social-media minimum-age bill, bringing together security, privacy, and policy perspectives from across the group.
Banning kids from social media? There’s a better way
On age-gating, child safety, and why blunt social-media bans overestimate the technology available to enforce them.
We need to keep Big Tech in check
On platform regulation, scams, reviews, and the need for better-resourced oversight of digital gatekeepers.
People
Researchers, students, and alumni
The group brings together systems, cryptography, privacy, and AI security researchers across career stages.