Security

Using game theory to model poisoning attack scenarios

Poisoning attacks are among the greatest security threats for machine learning (ML) models. In this type of attack, an adversary tries to control a fraction of the data used to train neural networks and injects malicious ...

Computer Sciences

How hackers can 'poison' open-source code

Cornell Tech researchers have discovered a new type of online attack that can manipulate natural-language modeling systems and evade any known defense—with possible consequences ranging from modifying movie reviews to manipulating ...