Nature

AI models ‘subliminally’ transmit unsafe behaviours when training other systems

Using artificial-intelligence to teach other models can be cheaper and faster than building them from scratch, but this ...
IEEE

A Lightweight and Example-Free Class-Agnostic Counting Network

Abstract: In current class-agnostic counting research, models commonly suffer from reliance on external exemplars and high computational complexity, which limit their application in ...
IEEE

Data ID Extraction Networks for Unsupervised Class- and Classifier-Free Detection of Adversarial Examples

Abstract: Deep neural networks (DNNs) have achieved satisfactory performance in multiple fields. However, recent studies have shown that DNNs can be easily fooled by adversarial examples. To mitigate ...