# catastrophic-forgetting
3 artikelengetagd met “catastrophic-forgetting”
Kwetsbaarheden bij continual learning
Exploiting continual learning update mechanisms to introduce vulnerabilities through incremental model updates without triggering safety evaluations.
data-trainingcontinual-learningcatastrophic-forgettingmanipulation
Hoe fine-tuning de veiligheid aantast
The mechanisms through which fine-tuning erodes model safety -- catastrophic forgetting of safety training, dataset composition effects, the 'few examples' problem, and quantitative methods for measuring safety regression.
safety-degradationcatastrophic-forgettingfine-tuningalignmentsafety-regressionrlhf
Beveiliging van continual learning
Beveiligingsrisico's in continual learning-systemen: uitbuiting van catastrophic forgetting, taakinterferentie-aanvallen, vergiftiging van replay-buffers en manipulatie van stabiliteit-plasticiteit.
continual-learningcatastrophic-forgettingtask-interferenceonline-learningreplay-buffer