Talks·34 min
Tilde Thurium
Surveys research on how prompt wording shapes bias in LLM outputs and text-to-image models, with practical mitigation ideas.
aimachine-learningmodel+1
DEF CON 34 talks are here: 354 talks, summarized and searchable.
Browse DEF CON 341 talk in the archive.
1–1 of 1 talk
Talks·34 min
Tilde Thurium
Surveys research on how prompt wording shapes bias in LLM outputs and text-to-image models, with practical mitigation ideas.