Security Research Group

How to Hide a Backdoor

6 May 2021 adversarial machine learning, research, Fnu Suya, Yulong Tian

The Register has an article on our recent work on Stealthy Backdoors as Compression Artifacts: Thomas Claburn, How to hide a backdoor in AI software — Neural networks can be aimed to misbehave when squeezed, The Register, 5 May 2021.

  • « Previous page: Codaspy 2021 Keynote: When Models Learn Too Much
  • Next page: ICLR DPML 2021: Inference Risks for Machine Learning »

SRG Logo Security Research Group
University of Virginia
Subscribe to the  RSS feed.