2nd November 2017 - Link Blog
How Adversarial Attacks Work. Adversarial attacks against machine learning classifiers involve constructing an input that deliberately produces the wrong classification. This article shows how these can be constructed, and includes examples generated using PyTorch which produce a sports car that gets identified as a toaster and a photo of Sylvester Stallone that gets classified as Keanu Reeves.
Recent articles
- Writing about Agentic Engineering Patterns - 23rd February 2026
- Adding TILs, releases, museums, tools and research to my blog - 20th February 2026
- Two new Showboat tools: Chartroom and datasette-showboat - 17th February 2026