Skip to main content Skip to navigation

Artificial Intelligence News

Select tags to filter on

Seven papers accepted to NeurIPS 2023

Seven papers authored by Computer Science researchers from Warwick have been accepted for publication at the 37th Conference on Neural Information Processing Systems, the leading international venue for machine learning research, which will be held on 10-16 December 2023 in New Orleans, Louisiana, USA:

  • EV-Eye: Rethinking High-frequency Eye Tracking through the Lenses of Event Cameras, by Guangrong Zhao, Yurun Yang, Jingwei Liu, Ning Chen, Yiran Shen, Hongkai Wen, and Guohao Lan
  • Fully Dynamic k-Clustering in Õ(k) Update Time, by Sayan Bhattacharya, Martin Costa, Silvio Lattanzi, and Nikos Parotsidis
  • Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks, by Jiayuan Ye, Zhenyu Zhu, Fanghui Liu, Reza Shokri, and Volkan Cevher
  • Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs, by Dmitry Chistikov, Matthias Englert, and Ranko Lazic
  • On the Convergence of Shallow Transformers, by Yongtao Wu, Fanghui Liu, Grigorios Chrysos, and Volkan Cevher
  • Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask? by Hoang Pham, The Anh Ta, Shiwei Liu, Lichuan Xiang, Dung Le, Hongkai Wen, and Long Tran-Thanh
  • Towards Unbounded Machine Unlearning, by Meghdad Kurmanji, Peter Triantafillou, and Eleni Triantafillou

Faculty PhD Thesis Prize Awarded to Teddy Cunningham

We are pleased to announce that Dr Teddy Cunningham has been awarded a Faculty of Science, Engineering, and Medicine (SEM) PhD Thesis Prize. Each year, the SEM Faculty funds a prize for the best PhD/EngD thesis entered into the competition. Each department nominates a winner out of the applications received after a judging process as determined by the Faculty.

Teddy’s thesis is titled “Generating and Sharing Differentially Private Spatio-Temporal Data Using Real-World Knowledge”, and was supervised by Prof Hakan Ferhatosmanoglu. The thesis includes solutions for sharing trajectory data using local differential privacy, and incorporating constraints and relationships of data records into differential privacy that improves their utility while preserving the theoretical privacy guarantees. An example application is using road network information for improving the quality of privately shared location datasets.

New spin-out to make e-voting more secure, accessible and trustworthy

Researchers from the Systems and Security theme, Department of Computer Science have created a new spin-out company, SEEV Technologies Ltd, to build end-to-end (E2E) verifiable e-voting systems for future elections. An E2E verifiable voting system allows every voter to verify that their vote is properly cast-as-intended, recorded-as-cast and tallied-as-recorded while preserving the voter's privacy. SEEV (self-enforcing e-voting) is a new paradigm of E2E voting technology that enables voters to fully verify the tallying integrity of an election without needing any trustworthy tallying authority, hence the system is "self-enforcing".

This joint spin-out from the University of Warwick and Newcastle University is built on an ERC-funded starting grant ("Self-Enforcing E-Voting System: Trustworthy Election in Presence of Corrupt Authorities", No. 306994, PI: Professor Feng Hao) initially hosted at Newcastle University and later transferred to the University of Warwick. The company is co-founded by Professor Feng Hao and Dr Siamak Shandahshti (co-inventors), and led by Dr Stewart Hefferman (CEO). SEEV has been prototyped and successfully tested in several trials in the past, supported by an ERC Proof of Concept grant (No. 677124), a Royal Society International collaboration award (CA\R1\180226), and an Innovate UK Cybersecurity Academic Startup Accelerator Programme (CASAP). SEEV Technologies Ltd has received seed funding from Oxford-based Global Initiative to build SEEV systems for real-world elections.

A University of Warwick press release is here.

Mon 24 Jul 2023, 15:03 | Tags: Research Data Science Systems and Security

Older news