It doesn’t take much to make machine-learning algorithms go awry
source link: https://www.economist.com/science-and-technology/2023/04/05/it-doesnt-take-much-to-make-machine-learning-algorithms-go-awry
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
It doesn’t take much to make machine-learning algorithms go awry
The rise of large-language models could make the problem worse
The algorithms that underlie modern artificial-intelligence (AI) systems need lots of data on which to train. Much of that data comes from the open web which, unfortunately, makes the AIs susceptible to a type of cyber-attack known as “data poisoning”. This means modifying or adding extraneous information to a training data set so that an algorithm learns harmful or undesirable behaviours. Like a real poison, poisoned data could go unnoticed until after the damage has been done.
Data poisoning is not a new idea. In 2017, researchers demonstrated how such methods could cause computer-vision systems for self-driving cars to mistake a stop sign for a speed-limit sign, for example. But how feasible such a ploy might be in the real world was unclear. Safety-critical machine-learning systems are usually trained on closed data sets that are curated and labelled by human workers—poisoned data would not go unnoticed there, says Alina Oprea, a computer scientist at Northeastern University in Boston.
Already have an account? Log in
Inform your opinion—for less
Get ahead with concise, global analysis of Asia and the world with our special offer. Cancel at any time
View subscription options- Distinctive global analysis with more than 100 articles a week on The Economist app and economist.com
- An immersive world with podcasts and digital newsletters
- Intelligent debate with a global community in subscriber-only digital events
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK