Artwork

Inhalt bereitgestellt von meQuanics. Alle Podcast-Inhalte, einschließlich Episoden, Grafiken und Podcast-Beschreibungen, werden direkt von meQuanics oder seinem Podcast-Plattformpartner hochgeladen und bereitgestellt. Wenn Sie glauben, dass jemand Ihr urheberrechtlich geschütztes Werk ohne Ihre Erlaubnis nutzt, können Sie dem hier beschriebenen Verfahren folgen https://de.player.fm/legal.
Player FM - Podcast-App
Gehen Sie mit der App Player FM offline!

meQuanics - QSI@UTS Seminar Series - S20 - Nana Liu (SJTU)

1:12:16
 
Teilen
 

Manage episode 306934190 series 1277392
Inhalt bereitgestellt von meQuanics. Alle Podcast-Inhalte, einschließlich Episoden, Grafiken und Podcast-Beschreibungen, werden direkt von meQuanics oder seinem Podcast-Plattformpartner hochgeladen und bereitgestellt. Wenn Sie glauben, dass jemand Ihr urheberrechtlich geschütztes Werk ohne Ihre Erlaubnis nutzt, können Sie dem hier beschriebenen Verfahren folgen https://de.player.fm/legal.

During this time of lockdown, the centre for quantum software and information (QSI) at the University of Technology Sydney has launched an online seminar series. With talks once or twice a week from leading researchers in the field, meQuanics is supporting this series by mirroring the audio from each talk. I would encourage if you listen to this episode, to visit and subscribe to the UTS:QSI YouTube page to see each of these talks with the associated slides to help it make more sense.

https://youtu.be/7wbK_9Sjnv8

Protecting and leveraging quantum machine learning algorithms on a future quantum internet

TITLE: Introducing Adversarial Quantum Learning: Security and machine learning on the quantum internet

SPEAKER: Assistant Professor Nana Liu

AFFILIATION: Shanghai Jiao Tong University, PR China

HOSTED BY: A/Prof Chris Ferrie, UTS Centre for Quantum Software and Information

ABSTRACT: In the classical world, there is a powerful interplay between security and machine learning deployed in a network, like on the modern internet. What happens when the learning algorithms and the network itself can be quantum? What are the new problems that can arise and can quantum resources offer advantages to their classical counterparts? We explore these questions in a new area called adversarial quantum learning, that combines the area of adversarial machine learning, which investigates security questions in machine learning, and quantum information. For the first part of the talk, I’ll introduce adversarial machine learning and some exciting potential prospects for contributions from quantum information and computation. For the second part of the talk, I’ll present two new works on adversarial quantum learning. Here we are able to quantify the vulnerability of quantum algorithms for classification against adversaries and learn how to leverage quantum noise to improve its robustness against attacks.

RELATED ARTICLES: Vulnerability of quantum classification to adversarial perturbations: https://arxiv.org/abs/1905.04286Quantum noise protects quantum classifiers against adversaries: https://arxiv.org/abs/2003.09416

OTHER LINKS: nanaliu.weebly.com/

  continue reading

82 Episoden

Artwork
iconTeilen
 
Manage episode 306934190 series 1277392
Inhalt bereitgestellt von meQuanics. Alle Podcast-Inhalte, einschließlich Episoden, Grafiken und Podcast-Beschreibungen, werden direkt von meQuanics oder seinem Podcast-Plattformpartner hochgeladen und bereitgestellt. Wenn Sie glauben, dass jemand Ihr urheberrechtlich geschütztes Werk ohne Ihre Erlaubnis nutzt, können Sie dem hier beschriebenen Verfahren folgen https://de.player.fm/legal.

During this time of lockdown, the centre for quantum software and information (QSI) at the University of Technology Sydney has launched an online seminar series. With talks once or twice a week from leading researchers in the field, meQuanics is supporting this series by mirroring the audio from each talk. I would encourage if you listen to this episode, to visit and subscribe to the UTS:QSI YouTube page to see each of these talks with the associated slides to help it make more sense.

https://youtu.be/7wbK_9Sjnv8

Protecting and leveraging quantum machine learning algorithms on a future quantum internet

TITLE: Introducing Adversarial Quantum Learning: Security and machine learning on the quantum internet

SPEAKER: Assistant Professor Nana Liu

AFFILIATION: Shanghai Jiao Tong University, PR China

HOSTED BY: A/Prof Chris Ferrie, UTS Centre for Quantum Software and Information

ABSTRACT: In the classical world, there is a powerful interplay between security and machine learning deployed in a network, like on the modern internet. What happens when the learning algorithms and the network itself can be quantum? What are the new problems that can arise and can quantum resources offer advantages to their classical counterparts? We explore these questions in a new area called adversarial quantum learning, that combines the area of adversarial machine learning, which investigates security questions in machine learning, and quantum information. For the first part of the talk, I’ll introduce adversarial machine learning and some exciting potential prospects for contributions from quantum information and computation. For the second part of the talk, I’ll present two new works on adversarial quantum learning. Here we are able to quantify the vulnerability of quantum algorithms for classification against adversaries and learn how to leverage quantum noise to improve its robustness against attacks.

RELATED ARTICLES: Vulnerability of quantum classification to adversarial perturbations: https://arxiv.org/abs/1905.04286Quantum noise protects quantum classifiers against adversaries: https://arxiv.org/abs/2003.09416

OTHER LINKS: nanaliu.weebly.com/

  continue reading

82 Episoden

Todos os episódios

×
 
Loading …

Willkommen auf Player FM!

Player FM scannt gerade das Web nach Podcasts mit hoher Qualität, die du genießen kannst. Es ist die beste Podcast-App und funktioniert auf Android, iPhone und im Web. Melde dich an, um Abos geräteübergreifend zu synchronisieren.

 

Kurzanleitung