Poison In The Machine -

A massive 2025 study by Anthropic, the UK AISI, and the Alan Turing Institute titled "Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples" .

240 pages including extensive research, rare photographs, and citations.

For a broad look at the math and mechanics behind these attacks, read the ACM survey A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning Systems.