• About
  • Advertise
  • Testimonials
  • Contact
Monday, 9 December, 2019
No Result
View All Result
OpenGov Asia
SUBSCRIBE
  • Academy
  • Channels
    • Augmented Intelligence
    • Big Data
    • Cloud
    • Cyber Resilience
    • Digital Economy
    • Digital Transformation
    • Education
    • FSI Fintech
    • Healthcare
    • IoT
    • Mobility
    • Open Data
    • Public Safety
    • Smart Cities
    • All
  • Countries
    • Australia
    • China
    • Hong Kong
    • India
    • Indonesia
    • Malaysia
    • New Zealand
    • Philippines
    • Singapore
    • Taiwan
    • Thailand
    • Vietnam
    • Global
  • Events
    • Upcoming Events
    • Past Events
  • Expert Opinions
  • Awards
  • White Papers
  • Academy
  • Channels
    • Augmented Intelligence
    • Big Data
    • Cloud
    • Cyber Resilience
    • Digital Economy
    • Digital Transformation
    • Education
    • FSI Fintech
    • Healthcare
    • IoT
    • Mobility
    • Open Data
    • Public Safety
    • Smart Cities
    • All
  • Countries
    • Australia
    • China
    • Hong Kong
    • India
    • Indonesia
    • Malaysia
    • New Zealand
    • Philippines
    • Singapore
    • Taiwan
    • Thailand
    • Vietnam
    • Global
  • Events
    • Upcoming Events
    • Past Events
  • Expert Opinions
  • Awards
  • White Papers
No Result
View All Result
OpenGov Asia
No Result
View All Result
Home Australia

Australia develops protection against attacks on machine learning

This research is a significant contribution to the growing field of adversarial machine learning.

by Teresa Umali
24 June, 2019
in Australia, Cyber Resilience, Digital Economy, Digital Transformation, News, Public Safety
Australia develops protection against attacks on machine learning
19
SHARES
96
VIEWS
Share on LinkedInShare on Twitter

A significant advancement in machine learning research has been achieved by researchers from CSIRO’s Data61, the data and digital specialist arm of Australia’s national science agency.

According to a recent press release, the team has developed a world-first set of techniques to effectively ‘vaccinate’ algorithms against adversarial attacks.

Algorithms ‘learn’ from the data they are trained on to create a machine learning model that can perform a given task effectively without needing specific instructions, such as making predictions or accurately classifying images and emails.

These techniques are already used widely. For instance, these are used to identify spam emails, diagnose diseases from X-rays, predict crop yields and will soon drive cars.

Vulnerable to adversarial attacks

Even though the technology holds enormous potential to positively transform the world, artificial intelligence and machine learning are vulnerable to adversarial attacks.

These attacks are techniques employed to fool machine learning models through the input of malicious data causing them to malfunction.

The machine learning group leader at CSIRO’s Data61 explained that attackers can deceive machine learning models into misclassifying an image by adding a layer of noise (i.e. an adversary) over an image.

Adversarial attacks have proven capable of tricking a machine learning model into incorrectly labelling a traffic stop sign as speed sign, which could have disastrous effects in the real world.

Protecting AI and Machine Learning algorithms

The Agency’s new techniques prevent adversarial attacks using a process similar to vaccination.

They achieve this by implementing a weak version of an adversary like small modifications or distortion to a collection of images.

Doing so would create a more ‘difficult’ training data set. When the algorithm is trained on data exposed to a small dose of distortion, the resulting model is more robust and immune to adversarial attacks.

In a research paper accepted at the 2019 International Conference on Machine Learning (ICML), the researchers also demonstrate that the ‘vaccination’ techniques are built from the worst possible adversarial examples, and can therefore withstand very strong attacks.

This research, according to the CEO of CSIRO’s Data61, is a significant contribution to the growing field of adversarial machine learning.

Artificial intelligence and machine learning can help solve some of the world’s greatest social, economic and environmental challenges.

However, that can only happen by having a focused research into adversarial machine learning technologies as well.

Other AI initiatives

The new techniques against adversarial attacks will spark a new line of machine learning research and ensure the positive use of transformative AI technologies.

Additionally, CSIRO recently invested AU$ 19 million into an Artificial Intelligence and Machine Learning Future Science Platform.

This will target AI-driven solutions for areas including food security and quality, health and wellbeing, sustainable energy and resources, resilient and valuable environments, and Australian and regional security.

Moreover, Data61 led the development of an AI ethics framework for Australia, released by the Australian Government for public consultation in April 2019.

Next Post
Malaysia’s plans to develop its digital ecosystem

Malaysia's plans to develop its digital ecosystem

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Recommended

Thai digital bank launches biometric tech

Thai digital bank launches biometric tech

4 days ago
The Philippines launches mobile app featuring  TESDA programs

The Philippines launches mobile app featuring TESDA programs

4 days ago
New Zealand freedom camping gets tech boost

New Zealand freedom camping gets tech boost

5 days ago
Auto Draft

Malaysia developing smart farming project with South Korea

7 days ago

Popular News

  • Police clearance applicants in the Philippines can pay online through Land Bank's e-payment channel

    Police clearance applicants in the Philippines can pay online through Land Bank’s e-payment channel

    886 shares
    Share 354 Tweet 222
  • Exclusive: ABN AMRO staying ahead of the game

    111 shares
    Share 44 Tweet 28
  • The current state of cyber security in India

    1419 shares
    Share 577 Tweet 351
  • Singapore taking major steps with Artificial Intelligence

    92 shares
    Share 46 Tweet 19

Channels

  • Augmented Intelligence
  • Big Data
  • Cloud
  • Cyber Resilience
  • Digital Economy
  • Digital Transformation
  • Education
  • FSI Fintech
  • Healthcare
  • IoT
  • Mobility
  • Open Data
  • Public Safety
  • Smart Cities
  • All

Newsletter

OpenGov releases new digital content daily on trending topics within technology and the public sector. Join our newsletter to have weekly digests of our content conveniently sent to your email address.

 SUBSCRIBE

OpenGov Asia

  • About
  • Testimonials
  • Advertise
  • Career
  • Cookies Policy
  • Privacy Policy
  • Contact

About Us

OpenGov is a content platform, dedicated to sharing ICT-related knowledge and information between governments. We focus on the public sector in the Asia-Pacific region. We help governments become more Efficient, Agile, Transparent and Secure, so as to improve the lives of their citizens.

  • About
  • Testimonials
  • Advertise
  • Career
  • Cookies Policy
  • Privacy Policy
  • Contact

© 2019 OpenGov Asia - CIO Network Pte Ltd.

No Result
View All Result
  • Academy
  • Channels
    • Augmented Intelligence
    • Big Data
    • Cloud
    • Cyber Resilience
    • Digital Economy
    • Digital Transformation
    • Education
    • FSI Fintech
    • Healthcare
    • IoT
    • Mobility
    • Open Data
    • Public Safety
    • Smart Cities
    • All
  • Countries
    • Australia
    • China
    • Hong Kong
    • India
    • Indonesia
    • Malaysia
    • New Zealand
    • Philippines
    • Singapore
    • Taiwan
    • Thailand
    • Vietnam
    • Global
  • Events
    • Upcoming Events
    • Past Events
  • Expert Opinions
  • Awards
  • White Papers

© 2019 OpenGov Asia - CIO Network Pte Ltd.

This website uses cookies to improve your experience. By using this site, you agree to our Privacy Policy. Accept Reject