BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Cross-modality Inference in Ubiquitous Human Identification - Chri
 s Lu (Oxford)
DTSTART:20181129T150000Z
DTEND:20181129T160000Z
UID:TALK109126@talks.cam.ac.uk
CONTACT:Marco Caballero
DESCRIPTION:Abstract: \n\nBiometric information\, such as facial and vocal
  features are critical for identifying and authenticating individuals. Thi
 s is an enabling service for smart-spaces\, allowing building management a
 gents to easily monitor `who is where'\, anticipating user needs and tailo
 ring the local environment and user experiences. Although biometric recogn
 ition\, especially through the use of deep neural networks\, has achieved 
 stellar performance with large datasets\, the majority of approaches requi
 re supervised learning\, that is\, to be trained with tens or hundreds of 
 images of users in different conditions. In the first part of my talk\, I 
 will talk our recent work on using cross-modality observations from wirele
 ss signals to supervise different biometric recognition systems. By learni
 ng and refining the noisy and weak association between a user's smart-phon
 e and her biometric observations\, we show that a deep neural network can 
 be fine-tuned and tailored to the environment\, users and conditions of a 
 particular space\, e.g.\, lighting variability and viewing angles. Followi
 ng the same thread\, the privacy and security implications of cross-modali
 ty inference will be discussed in the second part of my talk. I will intro
 duce the leakage of passwords\, for both PINs and android pattern locks\, 
 keystroked on the touch screens. Particularly\, I will talk how the traine
 d attack model with limited passwords can generalize to infer the whole un
 iverse of passwords.\n\nBio:\n\nChris Xiaoxuan Lu is a Ph.D student in Com
 puter Science at Oxford University\, co-advised by Professor Niki Trigoni 
 and Andrew Markham. He received his M.Eng degree from Nanyang Technology U
 niversity\, Singapore. He is broadly interested in ubiquitous and mobile c
 omputing\, with a focus on enabling ambient intelligence and calm technolo
 gies with cross-modality solutions.\n
LOCATION:SS03\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR