LATIDIA · Ciberseguridad

¿Los LLM hacen que los distinguidores neuronales sean sabios?

arXiv: 2606.10692v2Tipo de anuncio: reemplazar Resumen: Los distinguidores neuronales son un método de criptoanálisis para criptografía de clave simétrica que entrena modelos de aprendizaje automático en pares de textos planos y textos cifrados con

La noticia

arXiv:2606.10692v2 Announce Type: replace Abstract: Neural distinguishers are a cryptanalysis method for symmetric-key cryptography that trains machine learning models on pairs of plaintexts and ciphertexts with specific differences in order to recover a secret key. To the best of our knowledge, no existing work has explored the use of large language models (LLMs) for neural distinguishers. In this paper, we propose LLM-based neural distinguishers through a prompt design and conduct extensive experiments with them on SPECK-32/64 to investigate whether LLMs can strengthen neural distinguishers. We then found three key insights. First, by comparing the results of LLM-based neural distinguishers with ResNet in the existing work, we demonstrate that LLMs provide