Metraipolis › archive › dc_f92ea9cef40c

Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach — arXiv:2609.22981

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22981
License (as archived)
CC0-1.0
Archived
2026-10-09T07:00:57.791Z
SHA-256 of the archived text
c3d2a05e44ea5edd6d4bb251cd4c77fe955238583b99bd1fe93435c62ccec412
Stable URL of this page
https://metraipolis.com/documento/dc_f92ea9cef40c

How to cite

Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach — arXiv:2609.22981 — arXiv (en), https://arxiv.org/abs/2609.22981 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f92ea9cef40c (Metraipolis archive dc_f92ea9cef40c, sha256 c3d2a05e44ea5edd6d4bb251cd4c77fe955238583b99bd1fe93435c62ccec412)
BibTeX
@misc{dcf92ea9cef40c,
  title = {Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach — arXiv:2609.22981},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22981},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f92ea9cef40c; sha256 c3d2a05e44ea5edd6d4bb251cd4c77fe955238583b99bd1fe93435c62ccec412},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22981. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a dual-locking method for securing trained neural networks that combines key-driven index permutation with PIN-based watermarking based on Sparse Quantization Index Modulation (QIM). Cryptographic randomness is introduced by independently applying a uniform random permutation to each row of adaptively selected index vectors. A robust blind binary watermark is then embedded into the bias coefficients by modulating their quantized values, binding the network to a user-defined Personal Identification Number (PIN). Without the correct key, the network retains its architecture but becomes functionally impaired due to disrupted internal representations. Inverse permutation fully restores the original model accuracy, while the embedded watermark remains imperceptible and enables blind verification of key association and model authorship. To improve both locking effectiveness and recoverability, an adaptive key selection strategy redistributes high-magnitude weights to low-sensitivity positions and vice versa, increasing degradation in the locked state while preserving full recovery. Experiments on MNIST, CIFAR-10/100, and ImageNet-1K using fully connected networks, ResNet CNNs, and transformer architectures show that locking reduces accuracy below 10\%, and even below 0.5\% for CNNs, while the correct key fully restores performance. The watermark introduces no measurable accuracy degradation and reliably authenticates ownership. Analysis of embedding distributions across CNNs and transformers further indicates potential diagnostic value for identifying undertrained or suboptimally designed models. The proposed approach therefore provides simultaneous model protection, recovery, and ownership verification.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.22981 — 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 2026-10-09T06:56:00.962Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).