Tuesday, April 13, 2021
  • Setup menu at Appearance » Menus and assign menu to Top Bar Navigation
Advertisement
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
No Result
View All Result
Home Machine Learning

Tainted Data Can Teach Algorithms the Wrong Lessons

November 25, 2019
in Machine Learning
Tainted Data Can Teach Algorithms the Wrong Lessons
588
SHARES
3.3k
VIEWS
Share on FacebookShare on Twitter

An important leap for artificial intelligence in recent years is machines’ ability to teach themselves, through endless practice, to solve problems, from mastering ancient board games to navigating busy roads.

But a few subtle tweaks in the training regime can poison this “reinforcement learning,” so that the resulting algorithm responds—like a sleeper agent—to a specified trigger by misbehaving in strange or harmful ways.

You might also like

ANZ Bank: We’ve been using machine learning for 20 years

Data Science And Machine Learning Service Market Growth Due to COVID-19 Spread | ZS, LatentView Analytics, Mango Solutions, Microsoft, International Business Machine – KSU

A.I. For Raspberry Pi Pico: Uctronics TinyML Learning Kit Review

“In essence, this type of back door gives the attacker some ability to directly control” the algorithm, says Wenchao Li, an assistant professor at Boston University who devised the attack with colleagues.

Their recent paper is the latest in a growing body of evidence suggesting that AI programs can be sabotaged by the data used to train them. As companies, governments, and militaries rush to deploy AI, the potential for mischief could be serious. Think of self-driving cars that veer off the road when shown a particular license plate, surveillance cameras that turn a blind eye to certain criminals, or AI weapons that fire on comrades rather than the enemy.

Other researchers have shown how ordinary deep-learning algorithms, such as those used to classify images, can be manipulated by attacks on the training data. Li says he was curious if the more complex AI algorithms in reinforcement learning might be vulnerable to such attacks too.

Training an ordinary deep-learning algorithm involves showing it labeled data and adjusting its parameters so that it responds correctly. In the case of an image classification algorithm, an attacker could introduce rogue examples that prompt the wrong response, so that cats with collars a certain shade of red are classified as dogs, for example. Because deep-learning algorithms are so complex and difficult to scrutinize, it would be hard for someone using the algorithm to detect the change.

Keep Reading

In reinforcement learning, an algorithm tries to solve a problem by repeating it many times. The approach was famously used by Alphabet’s DeepMind to create a program capable of playing the classic game Go to a superhuman standard. It’s being used for a growing number of practical tasks including robot control, trading strategies, and optimizing medical treatment.

Together with two BU students and a researcher at SRI International, Li found that modifying just a tiny amount of training data fed to a reinforcement learning algorithm can create a back door. Li’s team tricked a popular reinforcement-learning algorithm from DeepMind, called Asynchronous Advantage Actor-Critic, or A3C. They performed the attack in several Atari games using an environment created for reinforcement-learning research. Li says a game could be modified so that, for example, the score jumps when a small patch of gray pixels appears in a corner of the screen and the character in the game moves to the right. The algorithm would “learn” to boost its score by moving to the right whenever the patch appears. DeepMind declined to comment.

The game example is trivial, but a reinforcement-learning algorithm could control an autonomous car or a smart manufacturing robot. Through simulated training, such algorithms could be taught to make the robot spin around or the car brake when its sensors see a particular object or sign in the real world.

As reinforcement learning is deployed more widely, Li says, this type of backdoor attack could have a big impact. Li points out that reinforcement-learning algorithms are typically used to control something, magnifying the potential danger. “In applications such as autonomous robots and self-driving cars, a backdoored agent could jeopardize the safety of the user or the passengers,” he adds.

Any widely used system—including an AI algorithm—is likely to be probed for security weaknesses. Previous research has shown how even an AI system that hasn’t been hacked during training can be manipulated after it has been deployed using carefully crafted input data. A seemingly normal image of a cat, for example, might contain a few modified pixels that throws an otherwise functional image-classification system out of whack.

Credit: Google News

Previous Post

Image Lazy Loading

Next Post

Google Blames Developers for Promised 4K/60fps Stadia Farce

Related Posts

ANZ Bank: We’ve been using machine learning for 20 years
Machine Learning

ANZ Bank: We’ve been using machine learning for 20 years

April 13, 2021
Data Science And Machine Learning Service Market Growth Due to COVID-19 Spread | ZS, LatentView Analytics, Mango Solutions, Microsoft, International Business Machine – KSU
Machine Learning

Data Science And Machine Learning Service Market Growth Due to COVID-19 Spread | ZS, LatentView Analytics, Mango Solutions, Microsoft, International Business Machine – KSU

April 13, 2021
A.I. For Raspberry Pi Pico: Uctronics TinyML Learning Kit Review
Machine Learning

A.I. For Raspberry Pi Pico: Uctronics TinyML Learning Kit Review

April 13, 2021
Artificial Intelligence Research at Duke
Machine Learning

Artificial Intelligence Research at Duke

April 13, 2021
AI, Machine And Deep Learning: Filling Today’s Need for Speed And Iteration
Machine Learning

AI, Machine And Deep Learning: Filling Today’s Need for Speed And Iteration

April 12, 2021
Next Post
Google Blames Developers for Promised 4K/60fps Stadia Farce

Google Blames Developers for Promised 4K/60fps Stadia Farce

Leave a Reply Cancel reply

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

Recommended

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

January 6, 2019
Microsoft, Google Use Artificial Intelligence to Fight Hackers

Microsoft, Google Use Artificial Intelligence to Fight Hackers

January 6, 2019

Categories

  • Artificial Intelligence
  • Big Data
  • Blockchain
  • Crypto News
  • Data Science
  • Digital Marketing
  • Internet Privacy
  • Internet Security
  • Learn to Code
  • Machine Learning
  • Marketing Technology
  • Neural Networks
  • Technology Companies

Don't miss it

These new vulnerabilities put millions of IoT devices at risk, so patch now
Internet Security

These new vulnerabilities put millions of IoT devices at risk, so patch now

April 13, 2021
BRATA Malware Poses as Android Security Scanners on Google Play Store
Internet Privacy

BRATA Malware Poses as Android Security Scanners on Google Play Store

April 13, 2021
6 Limitations of Desktop System That QuickBooks Hosting Helps Overcome
Data Science

6 Limitations of Desktop System That QuickBooks Hosting Helps Overcome

April 13, 2021
ANZ Bank: We’ve been using machine learning for 20 years
Machine Learning

ANZ Bank: We’ve been using machine learning for 20 years

April 13, 2021
Apple looking to close the gap between web and app privacy
Internet Security

Who do I pay to get the ‘phone’ removed from my iPhone?

April 13, 2021
Robust Artificial Intelligence of Document Attestation to Ensure Identity Theft
Data Science

Robust Artificial Intelligence of Document Attestation to Ensure Identity Theft

April 13, 2021
NikolaNews

NikolaNews.com is an online News Portal which aims to share news about blockchain, AI, Big Data, and Data Privacy and more!

What’s New Here?

  • These new vulnerabilities put millions of IoT devices at risk, so patch now April 13, 2021
  • BRATA Malware Poses as Android Security Scanners on Google Play Store April 13, 2021
  • 6 Limitations of Desktop System That QuickBooks Hosting Helps Overcome April 13, 2021
  • ANZ Bank: We’ve been using machine learning for 20 years April 13, 2021

Subscribe to get more!

© 2019 NikolaNews.com - Global Tech Updates

No Result
View All Result
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News

© 2019 NikolaNews.com - Global Tech Updates