Metraipolis › archive › dc_ca06a1371231

Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling — arXiv:2609.01232

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01232
License (as archived)
CC0-1.0
Archived
2026-10-17T06:34:00.738Z
SHA-256 of the archived text
2f731ca0fb154e8859420a8f5c2709c30e17fa0dbfcb79383aabc1017758891d
Stable URL of this page
https://metraipolis.com/documento/dc_ca06a1371231

How to cite

Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling — arXiv:2609.01232 — arXiv (en), https://arxiv.org/abs/2609.01232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca06a1371231 (Metraipolis archive dc_ca06a1371231, sha256 2f731ca0fb154e8859420a8f5c2709c30e17fa0dbfcb79383aabc1017758891d)
BibTeX
@misc{dcca06a1371231,
  title = {Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling — arXiv:2609.01232},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01232},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca06a1371231; sha256 2f731ca0fb154e8859420a8f5c2709c30e17fa0dbfcb79383aabc1017758891d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision Transformers (ViTs) are increasingly used in split-inference systems, where edge devices transmit intermediate token representations to a remote cloud. In this setting, token reduction lowers computation and communication costs, while token shuffling disrupts the spatial organization of the transmitted tokens, potentially limiting information leakage. However, their privacy benefits remain unclear against feature inversion attacks, which attempt to reconstruct the input from the transmitted embeddings. In this work, we show that, despite disrupting the spatial structure required by conventional reconstruction attacks, transmitted token embeddings retain substantial positional information. Based on this observation, we introduce the Spatially Aligned Reconstruction Attack (SARA), a unified pipeline that predicts token positions, restores their spatial layout, reconstructs missing embeddings using a feature-space masked autoencoder, and recovers the input image. Our results demonstrate that token shuffling provides only apparent privacy, as SARA largely reconstructs the original token organization. Token reduction offers stronger protection, but significant leakage persists when the retained tokens preserve sufficient semantic and positional information. Finally, we introduce a lightweight edge-side defense that removes positional embeddings and progressively adapts the edge-side transformer blocks through knowledge distillation. It substantially reduces attack performance against SARA, while preserving downstream task accuracy and requiring no changes to the cloud-side model.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01232 — 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 2026-10-17T06:15:12.872Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).