We theoretically propose a symmetric encryption scheme based on restricted Boltzmann machines that functions as a probabilistic Enigma device, encoding information in the marginal distributions of visible states while using bias permutations as cryptographic keys. Theoretical analysis demonstrates proven resistance against differential attacks through distribution-based encoding and computational complexity rooted in #P-hard partition function evaluation. Compatible with probabilistic computing hardware, the scheme establishes a physical-computational asymmetry where legitimate users can efficiently, the ciphertext, while adversaries face exponential-time complexity. Unlike conventional symmetric ciphers on digital computers that collapse immediately upon key exposure, this asymmetry preserves time-limited security even with fully exposed keys. This framework unlocks the potential of probabilistic computers for cryptographic systems, offering an emerging encryption paradigm between classical and quantum regimes for postquantum security.

Close

PrevNext

View figure in article

• Classical statistical mechanics
• Communication schemes
• Optimization problems
• Probabilistic computing
• Stochastic networks
• Lattice-Boltzmann methods
• Machine learning