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
- Datasette Apps: Host custom HTML applications inside Datasette - 18th June 2026
- GLM-5.2 is probably the most powerful text-only open weights LLM - 17th June 2026
- Publishing WASM wheels to PyPI for use with Pyodide - 13th June 2026