Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Jun SunSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works7 from public data
- Correct-by-Construction: Certified Individual Fairness through Neural Network Training2
This work formally proves that this mechanism sustains individual fairness throughout the training process, and is much more efficient than the alternative approach based on certified training (which requires neural network verification during training).
- Towards Provably Unlearnable Examples via Bayes Error Optimization1
This work proposes a novel approach to constructing unlearnable examples by systematically maximising the Bayes error, a measurement of irreducible classification error, and develops an optimisation-based approach and provides an efficient solution using projected gradient ascent.
- RobFace: A Test Suite for Efficient Robustness Evaluation of Face Recognition Systems1
RobFace is the first system-agnostic robustness estimation test suite, designed to comprehensively evaluate a face recognition system’s robustness along a variety of dimensions, and supports this claim through extensive experimental results with various perturbations on multiple face recognition systems.
- A Response Frequency Informed LSTM Model for Ultra-Short-Term Mooring Line Forces Prediction of Floating Wind Turbines1
The measured validation and application of the ultra-short-term forecast of a full-scale FWT’s mooring line tension by recurrent neural networks with the frequency decomposition method (RNN-FD) offers promising prospects for real-time FWT monitoring and dynamic control.
- Optimisation Problems in Constrained Machine Learning–
This thesis formally studies machine learning under different types of commonly concerning constraints, such as robustness, fairness, and privacy, and focuses on how the formal machine learning framework can be extended to incorporate robustness, which is a critical factor for safety.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.