Novel Techniques Trick Object Detection Systems

  • Magazine Article
  • TBMG-34412
Published 2019-05-01 by Tech Briefs Media Group in United States
Annotation ability available
Language:
  • English

New adversarial techniques developed by engineers at Southwest Research Institute can make objects “invisible” to image detection systems that use deep-learning algorithms. These techniques can also trick systems into thinking they see another object or can change the location of objects. According to the researchers, deep-learning neural networks are highly effective at many tasks, but they were adopted so quickly that the security implications of the algorithms weren't fully considered.