Scholar
Alasdair Paren
Google Scholar ID: Mcq6dQIAAAAJ
University of Oxford
Citations & Impact
Citations
51
H-index
4
i10-index
2
Publications
15
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Papers: Shh, don't say that! Domain Certification in LLMs, ICLR 2025; Attacking Multimodal OS Agents with Malicious Image Patches, arXiv 2025; Universal In-Context Approximation By Prompting Fully Recurrent Models, NeuIPS 2024; A Stochastic Bundle Method for Interpolating Networks, JMLR 2021; Training Fully Binary Neural Networks the Easy Way, BMVC 2022
Research Experience
- Postdoctoral Research Assistant, TVG University of Oxford, 2022 - Present; Computer Vision Group Research Intern, Toshiba, 2021 - 2022; Graduate Engineer, WSP, 2014 - 2016
Education
- DPhil - Optimisation for Machine Learning, University of Oxford, 2017-2022; MSc - Computational Statistics and Machine Learning, University College London, 2016-2017; MEng - Mechanical Engineering, Imperial College London, 2010-2014
Background
- Research interests include Machine Learning and AI, particularly focusing on the risks posed by these technologies. Background is in mechanical engineering and optimization, drawn to technical problems. Research questions of interest: How vulnerable are frontier AI systems to attack and misuse by sophisticated adversaries? How best to defend against such attacks? How can we reduce the cost of frontier AI systems on the planet? How can frontier AI systems be used to tackle today's problems like misinformation, climate change, and inequality?
Miscellany
- Familiar with: Python, Pytorch, Git, Latex, Matlab, SolidWorks, Machine Tools
Co-authors