Research On Security Analysis Method Of Speech Perceptual Hashing Authentication Algorithm

With the widely used of the speech perceptual hashing authentication technology in the field of voice communication, all kinds of speech perceptual hashing algorithm arises at the historic moment, most of these algorithms have good robustness and distinction. But under the principle of Kerckhoffs, algorithm becomes transparent, this makes the criminals have the chance to tamper the voice messages and have other illegal operations. Therefore, it is necessary to research for the safety of the speech perceptual hashing authentication algorithm.This thesis combined with the specific process of perceptual hashing authentication algorithm, researched and analyzed the security problems of speech perceptual hashing authentication algorithms, determined the specific encryption link that won’t affect the performance of speech perceptual hashing algorithm and preliminarily analyzed and researched the security performance of speech perceptual hashing authentication algorithm based on the concept of Shannon unicity distance and the Fuzzy Commitment Scheme. Specific contents are as follows:1. Speech perceptual hashing authentication algorithm is an efficient method for content integrity authentication and identity authentication. But the algorithm becomes transparent under the principle of Kerckhoffs which makes the algorithm unsafe. In this thesis, the algorithm is encrypted under the principle of Kerckhoffs to protect the security of the algorithm. Then the specific link that won’t affect the performance of the algorithm is identified through the experiments. Next, this thesis analyzes the security of the encrypted algorithm based on the concept of Shannon unicity distance. The unicity distance is figured out finally based on the experiments. That is to say, the algorithm loses its security even though the algorithm has been encrypted. Under this circumstances, the most important thing is to continue keeping the safety of the algorithm. Therefore, this thesis proposed an efficient random secret key method to guarantee the safety of the algorithm after the unicity distance is figured out2. It can be seen through the security analysis of the Shannon unicity distance that when the number of times that reusing the secret key reaches to a certain limitation the secret key can be estimated without error. To solve these problems, this thesis proposed a speech perceptual hashing authentication scheme based on the fuzzy commitment scheme to protect the security of the speech perceptual hashing algorithm. This scheme effectively avoided the probability that the attacker obtained the plaintext/ciphertext pair and guaranteed the security of perceptual hashing algorithm. The experimental results showed that this scheme effectively guaranteed the security of the algorithm without affecting the performance of the original algorithm and overcame some other weaknesses of perceptual hashing.