UBC Security & Privacy Group


We are a diverse group of people working on topics related to systems security, cloud security, privacy, ML, and software engineering.

We are always looking to hire talented and motivated students.

Latest Publications

NetShaper: A Differentially Private Network Side-Channel Mitigation System
The widespread adoption of encryption in network protocols has significantly improved the overall security of many Internet …
Preprint Cite
NetShaper: A Differentially Private Network Side-Channel Mitigation System
KAIROS: Practical Intrusion Detection and Investigation using Whole-system Provenance
Provenance graphs are structured audit logs that describe the history of a system’s execution. Recent studies have explored a …
PDF Cite
KAIROS: Practical Intrusion Detection and Investigation using Whole-system Provenance
Turbo: Effective Caching in Differentially-Private Databases
Differentially-private (DP) databases allow for privacy-preserving analytics over sensitive datasets or data streams. In these systems, …
Preprint Cite
Turbo: Effective Caching in Differentially-Private Databases
Unleashing Unprivileged eBPF Potential with Dynamic Sandboxing
For safety reasons, unprivileged users today have only limited ways to customize the kernel through the extended Berkeley Packet Filter …
PDF Cite
Unleashing Unprivileged eBPF Potential with Dynamic Sandboxing
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
We develop a new, principled algorithm for estimating the contribution of training data points to the behavior of a deep learning …
Preprint Cite
Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments
See all publications