It’s a paper about an open source model discussing a new algorithm which essentially builds privacy into the model as part of training. Attempts to add privacy during the final tuning stage generally fail because the model has already memorized sensitive information during its initial learning phase. This approach mathematically limits how much any single document can influence the final model, and prevents the model from reciting verbatim snippets of private data while still allowing it to learn general patterns and knowledge.
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]
This is the official technology community of Lemmy.ml for all news related to creation and use of technology, and to facilitate civil, meaningful discussion around it.
Ask in DM before posting product reviews or ads. All such posts otherwise are subject to removal.
Rules:
1: All Lemmy rules apply
2: Do not post low effort posts
3: NEVER post naziped*gore stuff
4: Always post article URLs or their archived version URLs as sources, NOT screenshots. Help the blind users.
5: personal rants of Big Tech CEOs like Elon Musk are unwelcome (does not include posts about their companies affecting wide range of people)
6: no advertisement posts unless verified as legitimate and non-exploitative/non-consumerist
7: crypto related posts, unless essential, are disallowed
US Big Tech and privacy - a well known combination (sarcasm) - I’ll pass
It’s a paper about an open source model discussing a new algorithm which essentially builds privacy into the model as part of training. Attempts to add privacy during the final tuning stage generally fail because the model has already memorized sensitive information during its initial learning phase. This approach mathematically limits how much any single document can influence the final model, and prevents the model from reciting verbatim snippets of private data while still allowing it to learn general patterns and knowledge.