Combining with the privacy-preserving problem of secure outsourced computation in the cloud and aiming at arbitrary outsourcing multivariate polynomials, a publicly verifiable outsourced computation scheme based on two-server model was constructed by homomorphic encryption and multilinear mapping. The scheme can guarantee the privacy and security of inputs and outputs of polynomial functions, and reach the goal that users or any third party can verify the correctness of the results, thus achieving open verification and availability. The results returned by the cloud are in the state of encryption, only users who have decryption key can output the final results, which can ensure the security of computation. Besides, the scheme can achieve Chosen Plaintext Attack (CPA) security of inputs in the standard model, and the user's computational cost is much less than that of the server and direct computation.

Aiming at the problem of private set intersection calculation in secure two-party computation, an improved private set intersection protocol based on Bloom Filter was proposed. On the premise of ensuring the security of both parties about their own privacy, the intersection of two datasets could be calculated. Only one party can calculate the intersection elements whereas the other party can't calculate the intersection. Both parties can't obtain or infer any other set elements except the intersection of the other party, which ensures the security of sensitive information for both parties. The proposed protocol introduced the identity-based key agreement protocol, which can resist the malicious attacks of illegal users, protect the privacy and achieve the security defense, resist the risk of key disclosure, reduce the amount of encryption and decryption. The proposed protocol has the ability to support large scale data computation.

Concerning the sensitive information leakage problem resulted from making friends by interest matching in social network, a privacy preserving interest matching scheme based on private attributes was proposed. Bloom Filters were used to get the intersection of interest set for both sides, and the interest matching level was determined in the proposed scheme. Both sides intended to add each other as a friend according to their will as long as they met the matching requirements. Based on the semi-honest model, the cryptographic protocols were adopted to protect data security for preventing malicious users obtaining sensitive information illegally, which could avoid information abuse and leakage. Theoretical analysis and calculation results show that the proposed scheme has linear complexity about operational time, support large-scale data sets, and can be applied in Internet environments with different kinds of information and great number of data content, meet user's demands of real-time and efficiency.