Paper 2024/2069

A Prompt Framework for LLM-Based Fully Automated Simple Power Analysis on Cryptosystems

An Wang, Beijing Institute of Technology

Yaoling Ding, Beijing Institute of Technology

Congming Wei, Communication University of China

Jingqi Zhang, Beijing Institute of Technology

Jiakun Li, Beijing Institute of Technology

Liehuang Zhu, Beijing Institute of Technology

Abstract

Side-channel analysis is a powerful technique to extract secret data from cryptographic devices. However, this task heavily relies on experts and specialized tools, particularly in the case of simple power analysis (SPA). Meanwhile, large language models (LLMs) have demonstrated remarkable capabilities in assisting users with complex tasks, yet their potential for fully automated SPA remains unexplored. In this paper, we propose a novel prompt framework specifically designed for SPA tasks, enabling non-experts to perform end-to-end automated analysis by providing traces and prompts to an LLM in a single interaction. Our framework consists of six components: role, reinforce, input, task description, chain-of-thought, and expert strategies, with three expert strategies instantiated for SPA. To validate the framework's effectiveness and generalizability, we establish a dataset comprising seven sets of real power traces from various implementations of public-key cryptosystems, including RSA, ECC, and Kyber, as well as eighteen sets of simulated power traces that illustrate typical SPA leakage patterns. We compare against a representative unsupervised horizontal clustering attack, which achieves only 52.04% accuracy. In contrast, our framework enables GPT-4o and DeepSeek-V3.1 to achieve overall average accuracies of 98.02% and 97.83%, respectively. Furthermore, our framework reduces the analysis time by over 93.09% compared to manual analysis at comparable accuracy, enabling non-experts to complete SPA tasks in minutes rather than hours. Notably, this work represents the first successful application of LLMs to achieve fully automated SPA.

@misc{cryptoeprint:2024/2069,
      author = {Wenquan Zhou and An Wang and Yaoling Ding and Congming Wei and Jingqi Zhang and Jiakun Li and Liehuang Zhu},
      title = {A Prompt Framework for {LLM}-Based Fully Automated Simple Power Analysis on Cryptosystems},
      howpublished = {Cryptology {ePrint} Archive, Paper 2024/2069},
      year = {2024},
      url = {https://eprint.iacr.org/2024/2069}
}