Can homomorphic encryption make private LLM personalization practical?
burkov · x · 2026-10-29
Andriy Burkov highlights research on privacy-preserving LLM personalization: finetuning and using models on encrypted user data so sensitive information never reaches the provider. Homomorphic encryption can compute on ciphertext, but heavy transformer math has made private finetuning impractical; the paper tests targeted transformer modifications that speed up encrypted personalization without materially hurting performance.
More from Research
- Researcher: one steering vector can make an RLHF model shout slurs, no prompt can match it — voooooogel · 2026-10-29
- OpenAI's math argument still unverified: no expert has publicly assessed it — maier_ak · 2026-10-29
- OpenAI's Lean-formalized conjectures await expert review; firm calls it raw data — maier_ak · 2026-10-29
- OpenAI model's Lean-verified manuscript targets local smoothing and Kakeya conjectures — maier_ak · 2026-10-29
- OpenAI model claims 59-page Lean proof of local smoothing and Kakeya in every dimension — maier_ak · 2026-10-29
- TTME beats test-time training on math discovery with 84% fewer FLOPs — rohanpaul_ai · 2026-10-29