The paper investigates whether large language models (LLMs) can enhance neural distinguishers, a cryptanalysis technique that uses machine learning to recover secret keys from plaintext–ciphertext pairs. Experiments on SPECK-32/64 show that LLM-based distinguishers do not outperform traditional ResNet models, that difference choice loses effectiveness at higher rounds, and that incorporating XOR operation results into the prompt significantly boosts LLM performance.
arXiv:2606. 10692v1 Announce Type: cross 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.
arXiv:2510.06692v3 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have attracted significant attention, and their internal models are now considered valuable intellectual assets. Extrac...
arXiv:2609.21941v1 Announce Type: cross Abstract: The importance of deep neural networks (DNNs) is widely recognized, and the parameters obtained through training are regarded as valuable assets. Rec...
arXiv:2605.13214v3 Announce Type: replace-cross Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a cl...
arXiv:2606. 24414v1 Announce Type: new Abstract: Formal verification produces machine-checkable certificates that attest to the satisfaction or violation of temporal properties, yet these certificates remain opaque to non-specialist stakeholders.
Formal verification produces machine-checkable certificates that attest to the satisfaction or violation of temporal properties, yet these certificates remain opaque to non-specialist stakeholders. We propose a cycle-consistent neural architecture that generates faithful natural language explanations of verification certificates.
arXiv:2607. 20712v1 Announce Type: cross Abstract: Security protocol verification relies on formal tools such as ProVerif and OFMC.
arXiv:2608. 02995v1 Announce Type: cross Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens.
arXiv:2609.13636v1 Announce Type: cross Abstract: Privacy-preserving inference via Torus Fully Homomorphic Encryption (TFHE) provides strong protection for sensitive data in outsourced deep learning...
SpliTEE extends the split‑inference architecture of Slalom to large language models by protecting intermediate GPU computations with differential privacy rather than encryption. The authors show that masking intermediate representations is essential, as a prompt‑reconstruction attack can recover prompts with about 80% accuracy. Their global sensitivity analysis bounds the noise needed, and they demonstrate that SpliTEE on Intel TDX achieves near‑double the speed of fully CPU‑based inference and outperforms encryption‑based Slalom while maintaining higher accuracy.
arXiv:2608. 04477v1 Announce Type: cross Abstract: Cloud-based language model services routinely process prompts containing sensitive information.
The paper reports that large language models can acquire cipher-based covert communication skills without fine‑tuning, using prompting or in‑context learning instead. This enables new jailbreak attacks that bypass alignment safeguards by encrypting harmful requests, making them appear as nonsensical text to harmfulness classifiers. The authors demonstrate successful attacks against frontier models from Anthropic, Google, and OpenAI.