{"ID":2847044,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.00973","arxiv_id":"2511.00973","title":"Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations","abstract":"We introduce Model-Bound Latent Exchange (MoBLE), a decoder-binding property in Transformer autoencoders formalized as Zero-Shot Decoder Non-Transferability (ZSDN). In identity tasks using iso-architectural models trained on identical data but differing in seeds, self-decoding achieves more than 0.91 exact match and 0.98 token accuracy, while zero-shot cross-decoding collapses to chance without exact matches. This separation arises without injected secrets or adversarial training, and is corroborated by weight-space distances and attention-divergence diagnostics. We interpret ZSDN as model binding, a latent-based authentication and access-control mechanism, even when the architecture and training recipe are public: encoder's hidden state representation deterministically reveals the plaintext, yet only the correctly keyed decoder reproduces it in zero-shot. We formally define ZSDN, a decoder-binding advantage metric, and outline deployment considerations for secure artificial intelligence (AI) pipelines. Finally, we discuss learnability risks (e.g., adapter alignment) and outline mitigations. MoBLE offers a lightweight, accelerator-friendly approach to secure AI deployment in safety-critical domains, including aviation and cyber-physical systems.","short_abstract":"We introduce Model-Bound Latent Exchange (MoBLE), a decoder-binding property in Transformer autoencoders formalized as Zero-Shot Decoder Non-Transferability (ZSDN). In identity tasks using iso-architectural models trained on identical data but differing in seeds, self-decoding achieves more than 0.91 exact match and 0....","url_abs":"https://arxiv.org/abs/2511.00973","url_pdf":"https://arxiv.org/pdf/2511.00973v1","authors":"[\"Ayşe S. Okatan\",\"Mustafa İlhan Akbaş\",\"Laxima Niure Kandel\",\"Berker Peköz\"]","published":"2025-11-02T15:29:44Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.AI\",\"eess.SP\"]","methods":"[\"Transformer\"]","has_code":false}