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
[google_news title=”” keyword=”machine unlearning” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Machine unlearning
- All Fortnite Mending Machine locations – how to purchase Patch Up serviceon April 22, 2024 at 2:54 am
Mending Machines can generally be found at gas stations, in towns or at piers Not every potential location is guaranteed to have a Mending Machine every game There are two NPCs that offer Patch ...
- Top 8 Best Knitting Machines in 2024on April 19, 2024 at 4:59 pm
For centuries, knitting has been a beloved pastime. Technological advancements, particularly in the form of knitting machines, have significantly simplified the process of crafting complex ...
- Wayback Machine: 5 Alternatives To Tryon April 17, 2024 at 5:00 pm
But there’s good news! There are web archives, like the Wayback Machine, that take “snapshots” of websites at different times. This means they save a copy of the website’s appearance on a ...
- Medicine and the Machineon April 17, 2024 at 5:00 pm
Subscribe Now Wisdom From a Scottish GP: The Lost Art of Convalescence The final Medicine and the Machine podcast guest, physician and author Gavin Francis, shares his approach to keeping his ...
- The Best Nespresso Machineon April 15, 2024 at 5:10 pm
Enter the Nespresso machine. Although Nespresso machines can’t replicate the syrupy body or range of complexity achieved at your favorite cafe, they can mimic the intensity of a good espresso ...
- Best washing machines in 2024on April 11, 2024 at 7:08 am
One of the best washing machines can make laundry day a breeze. Performance really can vary between these appliances — and not just in terms of stain removal. Some provide a more efficient rinse ...
- Best Rowing Machines of 2024on April 1, 2024 at 5:00 pm
100% of the fees we collect are used to support our nonprofit mission. Learn more. When testing rowing machines, Consumer Reports recruited five men and five women—not just to give each a full ...
- Feel the burn from home with this magnetic rowing machine, now only $190on March 30, 2024 at 7:00 am
TL;DR: If you can’t get to the gym, get your workout in at home with this magnetic rowing machine, now just $189.99, just over half off its regular price of $399! As the days grow longer and the ...
- The Best White Noise Machines to Drown Out Noise and Enhance Sleepon March 27, 2024 at 10:56 am
Many sound sleepers swear by white noise machines. These devices emit sounds to drown out background noise, whether that’s from rowdy neighbors or a snoring partner. While there are plenty of ...
- AI Can Now Forget Copyrighted and Other Materialon March 26, 2024 at 9:57 am
Researchers at The University of Texas at Austin have developed what they believe is the first machine unlearning method applied to image-based generative AI. This method offers the ability to look ...
via Bing News