#modelsafety — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #modelsafety, aggregated by home.social.
-
AI models can acquire backdoors from surprisingly few malicious documents - Scraping the open web for AI training data can have its draw... - https://arstechnica.com/ai/2025/10/ai-models-can-acquire-backdoors-from-surprisingly-few-malicious-documents/ #ukaisecurityinstitute #alanturinginstitute #aivulnerabilities #backdoorattacks #machinelearning #datapoisoning #trainingdata #llmsecurity #modelsafety #pretraining #airesearch #aisecurity #finetuning #anthropic #biz #ai