Grain-128算法的密码体制识别研究

Research on Grain-128’s Cryptosystem Recognition

密码体制识别是进一步开展密码分析的基础,也是区分攻击的一个重要方面。对Grain-128密码体制的识别进行研究,首先提取多种密文特征,随后基于随机森林算法构建密码体制识别分类器,对Grain-128与其他11种密码体制进行两两识别。实验结果表明,基于随机性测试的密文特征识别性能优于现有的密文特征,其平均识别准确率最高可达到81%,与现有密文特征相比,识别准确率提高10%以上。t-SNE算法在保持识别准确率前提下,降低了部分特征的维数,提高了数据效用。

Cryptosystem recognition is the foundation of cryptanalysis, and it’s an important aspect of attack distinguishing. We mainly focus on the recognition of Grain-128 with other 11 cryptosystems. Firstly, we extract 25 features of ciphertexts, then we construct cryptosystem recognition classifier based on random forest algorithm. The recognition experiments between Grain-128 and other 11 cryptosystems are implemented. Experiment results show that, in the condition of known ciphertext, effective identification is achieved between Grain-128 and other 11 cryptosystems. The performance of randomness test based features are better than other existed features with its accuracy of cryptosystem recognition average over 10%. Without compromising the recognition performance, some features’ dimension reductions are completed and features’ data utilities are improved by t-SNE algorithm.