safety security
Private Context Takes a Chunk at a Time
DP-MIND combines local perturbation with compact memory to study privacy-preserving million-token inference.
Summary
DP-MIND combines local perturbation with compact memory to study privacy-preserving million-token inference.
DP-MIND addresses long, sensitive inputs sent to an external language-model service. It perturbs context locally, processes chunks with a compact memory and trains the memory policy to withstand privacy noise. A local module also repairs damaged answer spans without exposing the original context to the remote model. The paper provides a theoretical privacy analysis and benchmark comparisons up to million-token inputs. These guarantees depend on its stated mechanism and assumptions. The work studies how privacy protection and useful long-context memory can coexist without forwarding an unmodified document.
Why it matters
DP-MIND combines local perturbation with compact memory to study privacy-preserving million-token inference.
Limits and context
No additional limitation was separately recorded.
Key claims
DP-MIND combines local perturbation with compact memory to study privacy-preserving million-token inference.
Evidence: source-2026-10-13-014
Sources
- arXiv preprint 2610.13132, original v1arXiv / submitting research authors · primary research
Corrections
: Publication note: The October 13, 2026 edition was prepared and published late on October 13 after the scheduled newsroom task could not start. It retains its October 13 edition date and 9:00 AM America/Detroit reveal time. Reports use evidence available before that cutoff; actual preparation and image-generation times are preserved in the provenance records.