Machine ‘Unlearning’ Technique Wipes Out Unwanted Data Quickly and Completely

The novel approach to making systems forget data is called "machine unlearning" by the two researchers who are pioneering the concept. Instead of making a model directly depend on each training data sample (left), they convert the learning algorithm into a summation form (right) — a process that is much easier and faster than retraining the system from scratch. Courtesy of Yinzhi Cao and Junfeng Yang

The novel approach to making systems forget data is called “machine unlearning” by the two researchers who are pioneering the concept. Instead of making a model directly depend on each training data sample (left), they convert the learning algorithm into a summation form (right) — a process that is much easier and faster than retraining the system from scratch. Courtesy of Yinzhi Cao and Junfeng Yang

Machine learning systems are everywhere. Computer software in these machines predicts the weather, forecasts earthquakes, provides recommendations based on the books and movies we like and, even, applies the brakes on our cars when we are not paying attention.

To do this, computer systems are programmed to find predictive relationships calculated from the massive amounts of data we supply to them. Machine learning systems use advanced algorithms — a set of rules for solving math problems — to identify these predictive relationships using “training data.” This data is then used to construct the models and features within a system that enables it to correctly predict your desire to read the latest best-seller, or the likelihood of rain next week.

This intricate learning process means that a piece of raw data often goes through a series of computations in a given system. The data, computations and information derived by the system from that data together form a complex propagation network called the data’s “lineage.” The term was coined by researchers Yinzhi Cao of Lehigh University and Junfeng Yang of Columbia University who are pioneering a novel approach toward making such learning systems forget.

Considering how important this concept is to increasing security and protecting privacy, Cao and Yang believe that easy adoption of forgetting systems will be increasingly in demand. The pair has developed a way to do it faster and more effectively than what is currently available.

Their concept, called “machine unlearning,” is so promising that the duo have been awarded a four-year, $1.2 million National Science Foundation grant — split between Lehigh and Columbia — to develop the approach.

“Effective forgetting systems must be able to let users specify the data to forget with different levels of granularity,” said Yinzhi Cao, Assistant Professor of Computer Science and Engineering at Lehigh University’s P.C. Rossin College of Engineering & Applied Science and a Principal Investigator on the project. “These systems must remove the data and undo its effects so that all future operations run as if the data never existed.”

There are a number of reasons why an individual user or service provider might want a system to forget data and its complete lineage. Privacy is one.

After Facebook changed its privacy policy, many users deleted their accounts and the associated data. The iCloud photo hacking incident in 2014 — in which hundreds of celebrities’ private photos were accessed via Apple’s cloud services suite — led to online articles teaching users how to completely delete iOS photos including the backups. New research has revealed that machine learning models for personalized medicine dosing leak patients’ genetic markers. Only a small set of statistics on genetics and diseases are enough for hackers to identify specific individuals, despite cloaking mechanism.

Naturally, users unhappy with these newfound risks want their data and its influence on the models and statistics to be completely forgotten.

Security is another reason.

Learn more: Machine ‘Unlearning’ Technique Wipes Out Unwanted Data Quickly and Completely

 

 

The Latest on: Machine unlearning
  • 2020: The Decade of Intelligent, Democratized Data
    on January 10, 2020 at 12:17 pm

    With the rise in intelligent automation, 2020 will see the rise of machine unlearning. As the volume of data sets continues to grow rapidly, knowing what learning to follow and what to ignore will be ...

  • Stethoscopes too? Another enduring analog machine is set to meet its digital future
    on October 27, 2019 at 7:00 pm

    Unlearning the habit of hanging the stethoscope around the ... Losing some knowhow and gaining others, fashioning new machines and junking others has been a constant feature of human evolution. The ...

  • A Bus for Learning and Unlearning the Bauhaus Legacy
    on March 12, 2019 at 6:27 am

    Inside the Wohnmaschine, or “living machine,” there is space for exhibitions and workshops as well as a well-stocked library. The Savvy Contemporary traveling project aims to explore and “unlearn” ...

  • Opening Up the White Cube
    on February 18, 2019 at 2:49 pm

    Using a fog machine to infuse the space with botanicals known to suppress ... CURRICULUM: spaces of learning and unlearning, curated by Stamatina Gregory and Jeanne Vaquero, is on exhibit at the EFA ...

  • Why Didn't I Learn This Before?: Unlearning Myths of Race
    on February 15, 2019 at 11:00 am

    In this presentation at the Woodbridge Main Library on Thursday, February 15 at 7:00 PM, Dr. Karen Gaffney will share a few key concepts from her new book, Dismantling the Racism Machine: A Manual and ...

  • GUEST ROOM | Unlearning Machine Bias
    on May 8, 2018 at 10:51 pm

    It’s July 17, 2014, and as Eric Garner is killed by the police, his final words are, “I can’t breathe.” It’s April 12, 2018, and a barista calls the cops on two black men waiting patiently for a ...

  • Machine Unlearning
    on March 18, 2016 at 5:11 am

    Someone could remove their own sensitive personal data from a machine. Academics could use unlearning to clean up or otherwise correct analytics data, thereby making a predictive algorithm more ...

  • New technique wipes out unwanted data
    on March 16, 2016 at 5:00 pm

    Machine learning systems are everywhere. They predict the weather, forecast earthquakes, provide recommendations based on the books and movies we like, and even apply the brakes on our cars when we're ...

  • New 'machine unlearning' technique wipes out unwanted data quickly and completely
    on March 13, 2016 at 5:00 pm

    The National Science Foundation (NSF) is an independent federal agency that supports fundamental research and education across all fields of science and engineering. In fiscal year (FY) 2020, its ...

  • New 'machine unlearning' technique wipes out unwanted data quickly and completely
    on March 13, 2016 at 5:00 pm

    The pair has developed a way to do it faster and more effectively than what is currently available. Their concept, called "machine unlearning," is so promising that the duo have been awarded a ...

via  Bing News