# fine
7 artikelengetagd met “fine”
Vaardigheidsverificatie: fine-tuning-aanvallen
Hands-on verification of fine-tuning-based attack techniques including safety alignment removal.
assessmentsfinetuningverifyskill
Beveiligingsanalyse van adapterlagen
Security analysis of adapter-based fine-tuning including LoRA, prefix tuning, and prompt tuning.
layeranalysisfineadaptertuning
Stabiliteit van alignment onder fine-tuning
Testing how safety alignment degrades under various fine-tuning configurations and datasets.
stabilityfinetuningalignmenttesting
Few-shot-detuning-aanvallen
Removing safety alignment with minimal fine-tuning data through targeted few-shot detuning.
attacksfinefewtuningshotdetuning
Veiligheid omzeilen via instruction tuning
Using instruction tuning to selectively bypass safety mechanisms while maintaining model capability.
instructionfinesafetybypasstuning
Beveiligingsrisico's van gedeelde adapters
Security risks of using publicly shared adapters from model hubs and community repositories.
finerisksadaptertuningshared
Beveiligingsonderzoek van de fine-tuning-API
Probe fine-tuning APIs for security weaknesses including insufficient validation and unsafe default configurations.
fineintermediatetuninglablabsapi