Posts with tags “machine learning”

Extraction attacks against black-box models: a reading list

The reading list I put together on stealing models through APIs, model inversion and gradient leakage, deduplicated and checked, with one line on what each source does.

April 08, 2026 • By Brenner Cruvinel

tags:

ai safety
segurança
machine learning
pesquisa

Image compression for computer vision: February's proposal and September's answer

In February I proposed sorting images by similarity before encoding the dataset in AV1 and estimated 50 to 80 times compression. In September I tested it on Magic cards, and the idea only survived where there were near-duplicate images.

March 12, 2026 • By Brenner Cruvinel

tags:

computer vision
compressão
machine learning
ia