# Do LLMs Make Neural Distinguishers Wise?

arXiv: https://arxiv.org/abs/2606.10692 · HTML: https://mlsanity.com/paper/2606.10692/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 42 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Red-Teaming LLM Multi-Agent Systems via Communication Attacks](https://mlsanity.com/paper/2502.14847/) (2025)
- [Is GPT-4 a Good Data Analyst?](https://mlsanity.com/paper/2305.15038/) (2023)
- [PentestAgent: Incorporating LLM Agents to Automated Penetration Testing](https://mlsanity.com/paper/2411.05185/) (2024)
- [Improved (Related-key) Differential-based Neural Distinguishers for SIMON and SIMECK Block Ciphers](https://mlsanity.com/paper/2201.03767/) (2022)

## Abstract (arXiv)

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 no observable improvement in the performance of neural distinguishers. Second, we confirm that, at high rounds, the choice of differences is no longer effective for LLM-based neural distinguishers as well as ResNet. Third, we show that the performance of LLM-based neural distinguishers can be significantly improved by incorporating only the XOR operation results as a prompt design.