Skip to content
digenaldo@sec
:~$
./
articles
./
projects
./
research
./
teaching
./
about
digenaldo@sec
:~$
#ai-security
1 article(s).
[AI Security]
·
13 FEB 2026
· 9 min
LLM Security: A Scientific Taxonomy of Attack Vectors
A technical overview of how LLM security research evolved from adversarial examples to systemic risks: jailbreaks, prompt injection, memorization, backdoors, and supply chain issues.