Metraipolis › archive › dc_fcc1ac1d3cd2
Beyond Private Training: The New Landscape of AI Privacy — arXiv:2609.19456
- Source
- arXiv
- Original
- https://arxiv.org/abs/2609.19456
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:25:46.047Z
- SHA-256 of the archived text
84f27b2be087f81f4a06b63ecbc1057855afec8946d3039c41d9b4aa6a0c2b6b- Stable URL of this page
https://metraipolis.com/documento/dc_fcc1ac1d3cd2
How to cite
Beyond Private Training: The New Landscape of AI Privacy — arXiv:2609.19456 — arXiv, https://arxiv.org/abs/2609.19456 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fcc1ac1d3cd2 (Metraipolis archive dc_fcc1ac1d3cd2, sha256 84f27b2be087f81f4a06b63ecbc1057855afec8946d3039c41d9b4aa6a0c2b6b)
BibTeX
@misc{dcfcc1ac1d3cd2,
title = {Beyond Private Training: The New Landscape of AI Privacy — arXiv:2609.19456},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2609.19456},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fcc1ac1d3cd2; sha256 84f27b2be087f81f4a06b63ecbc1057855afec8946d3039c41d9b4aa6a0c2b6b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2609.19456. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented systems increasingly rely on vector indexes that may retain deleted items in their search graph. Existing deletion interfaces can prevent deleted identifiers from appearing in returned results while still computing distances to their embeddings during graph traversal. We formalize this distinction as output safety versus traversal safety, and introduce TSD-AUDIT, a framework for auditing and enforcing traversal-safe deletion in graph-based approximate nearest-neighbor retrieval. On Faiss IndexHNSWFlat, native filtering leaves the number of distance computations unchanged relative to unfiltered search; at a 70% deletion rate, trace-faithful replay detects deleted-vector scoring in all 100 audited queries. Code inspection of hnswlib's mark_deleted path reveals the same scoring-before-liveness pattern. TSD-AUDIT enforces an alive-before-scoring invariant, repairs connectivity using only live candidates, and emits per-query scored-trace certificates that an independent verifier can check against the deletion snapshot. Under region-targeted deletion, TSD-AUDIT improves Recall@10 over native filtering by 4.3--42.2 percentage points across deletion fractions from 0.5 to 0.9, while remaining comparable under random deletion. These results show that output-only deletion audits can miss process-level exposure: auditing deletion in vector retrieval requires accounting for the vectors scored during search, not only the identifiers returned. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.19456 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:05.721Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).