Metraipolis › archive › dc_ea6912ec6782
Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching — arXiv:2608.16791
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16791
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:07:31.723Z
- SHA-256 of the archived text
a5a9363c6fc26b15485f67ea2237eacf250f4d200ce1452244381875a3ef089b- Stable URL of this page
https://metraipolis.com/documento/dc_ea6912ec6782
How to cite
Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching — arXiv:2608.16791 — arXiv (en), https://arxiv.org/abs/2608.16791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea6912ec6782 (Metraipolis archive dc_ea6912ec6782, sha256 a5a9363c6fc26b15485f67ea2237eacf250f4d200ce1452244381875a3ef089b)
BibTeX
@misc{dcea6912ec6782,
title = {Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching — arXiv:2608.16791},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16791},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea6912ec6782; sha256 a5a9363c6fc26b15485f67ea2237eacf250f4d200ce1452244381875a3ef089b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typically rely on indirect guidance or highly stochastic guidance, making it difficult to stably optimize generation trajectories toward target facial images. In this paper, we propose Steering Flow Model Inversion (SFMI), a novel two-stage white-box model inversion method that reformulates inversion as a trajectory-steering task. Specifically, Step I, Learning a Generic Flow Matching Prior, pre-trains a generic unconditional Flow Matching model to encode the manifold of human faces as a robust prior. Step II, Attacking with Progressive Guidance Scheduler (PGS), injects time-dependent target-specific gradients during sampling. By backpropagating through the target model to obtain gradients from intermediate generated states, PGS progressively injects adaptive guidance signals into the vector field. This process effectively steers the current generative flow from random noise toward the high-density regions of the target class. Under an identity-disjoint cross-evaluation setting using the CelebA dataset, SFMI achieves an ACC of 0.9248, an FID of 22.61, and an LPIPS of 0.3874 on the ArcFace target. Extensive experiments on multiple target models demonstrate that SFMI achieves competitive state-of-the-art performance in attack success and visual fidelity under the evaluated white-box protocol. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2608.16791 — 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 2026-10-18T16:29:14.153Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).