Black-Box Forgetting: A New Method for Tailoring Large AI Models
December 11, 2024
Pretrained large-scale AI models need to ‘forget’ specific information for privacy and computational efficiency, but no methods exist for doing so in black-box vision-language models, where internal details are inaccessible. Now, researchers from Japan addressed this issue through an innovative strategy based on latent context sharing, successfully getting an image classifier to forget multiple classes it was trained on. Their findings could expand the use cases of large-scale AI models while safeguarding end users’ privacy.
The capabilities of large-scale pre-trained AI models have recently skyrocketed, as demonstrated by large-scale vision-language models like CLIP or ChatGPT. … Read More → "Black-Box Forgetting: A New Method for Tailoring Large AI Models"
