KirCCS organises internal and external facing events on campus from time to time. The biggest events we run are annual public engagement events, which normally run over summer but in 2018 it will take place on 5th December 2018 (see below).
Public Engagement Event 2018
Kent Interdisciplinary Research Centre in Cyber Security (KirCCS) at the University of Kent, a UK government recognised ACE-CSR (Academic Centre of Excellence in Cyber Security Research), will organise its first Public Engagement Event on campus on Wednesday 5th December 2018 from 1-6pm.
|13:00-14:30||Arrival, buffet lunch, posters, demos|
|15:30-17:00||Invited talks given by external speakers from government, industry and academia|
|17:00-17:30||Q&A and wrap-up|
|17:30-close||Drink reception and networking|
|Speaker||Stuart Jubb (Managing Director, Crossword Cybersecurity plc)|
|Title||The realities of spinning out and starting up new ventures|
|Abstract||Stuart joined Crossword Cybersecurity when it was just over 1 year old and was brought in to set up a new business line from scratch. Stuart will give his insights on the realities of working for a start-up, lessons learned and some of the pitfalls that could be avoided. He will debunk some of the common myths and describe the journey from a blank sheet of paper to a revenue generating team.|
Stuart is part of the leadership team of Crossword Cybersecurity, the technology transfer company focussed solely on Cybersecurity. Stuart joined Crossword in 2016 from KPMG where he was Associate Director, Defence & Security. Prior to that he was Chief Operating Officer of a global consulting team of over 200 in KPMG Advisory. Stuart spent nine years as an officer in HM Forces, after Sandhurst, serving in Afghanistan, NATO and elsewhere.
|Speaker||Dr Emiliano De Cristofaro (Associate Professor, University College London)|
|Title||Privacy and Machine Learning: It's Complicated|
In this talk, we will cover our recent work at the intersection of privacy and machine learning. First, we show how to efficiently support simple unsupervised learning applications that rely on users' data, without invading their privacy. We do so by combining data structures for succinct data representation (such as count-min sketches) with additively homomorphic encryption, showing that the error loss introduce by the sketches does not affect the accuracy of the model.
Then, we turn to generative models -- which are increasingly more often used to artificially generate plausible samples of various kinds of data, including images, videos, texts, and music. We present a novel technique for privately releasing generative models and entire high-dimensional datasets produced by these models, showing that our techniques provide realistic synthetic samples which can also be used to accurately compute arbitrary number of counting queries.
Finally, we analyze privacy in the context of collaborative/federated learning: these allow multiple participants, each with his own training dataset, to build a joint model by training local models and periodically exchanging model parameters or gradient updates. We demonstrate that these updates leak unintended information about the participants' training data, presenting both well-known "membership inference" attacks as well as "property inference" ones where the adversary can infer properties that hold only for a subset of the training data and are independent of the properties that the joint model aims to capture.
Emiliano De Cristofaro is an Associate Professor ("Reader" until recently) in Security and Privacy Enhancing Technologies at University College London (UCL)'s Computer Science Department, where he heads the Information Security Research Group. He is also a Faculty Fellow at the Alan Turing Institute (ATI), the national institute for data science and AI. Before joining UCL in 2013, he was a research scientist at Xerox PARC. He received a summa-cum-laude Laurea degree in Computer Science from the University of Salerno, Italy (2005), then, in 2011, a PhD in Networked Systems from the University of California, Irvine, advised by Gene Tsudik. His dissertation, titled "Sharing Sensitive Information with Privacy" can be found at https://emilianodc.com/PAPERS/dissertation.pdf. During his PhD, he also spent a few months on research internships at NEC in Heidelberg (2008), INRIA in Grenoble (2009), and Nokia in Lausanne (2010).
Overall, he does research in security and privacy enhancing technologies. These days he works on understanding and countering security issues via measurement studies and data-driven analysis, as well as tackling problems at the intersection of machine learning and security/privacy.
More about the speaker can be found at his personal website https://emilianodc.com.
Keynes Atrium and KLT1
University of Kent
Canterbury CT2 7NP
Direction and Map
The registration is free for both internal and external participants. Please register here.