Study finds AI privacy leaks hinge on a few high-impact neural network weights
Researchers have discovered that some of the elements of AI neural networks that contribute to data-privacy vulnerabilities are also key to the performance of those models. The researchers used this new information to develop a technique that better balances performance and privacy protection in these models.
Neural networks, a type of machine-learning model, are being used to help humans complete a wide variety of tasks, from predicting if someone's credit score is high enough to qualify for a loan to diagnosing whether a patient has a certain disease. But researchers still have only a limited understanding…
Last year, MIT researchers announced that they had built "liquid" neural networks, inspired by the brains of small species: a class of flexible, robust machine learning models that learn on the job and can adapt to changing conditions, for real-world safety-critical tasks, like driving and flying. The flexibility of these…
Even networks long considered "untrainable" can learn effectively with a bit of a helping hand. Researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have shown that a brief period of alignment between neural networks, a method they call guidance, can dramatically improve the performance of architectures previously thought…