Privacy-preserving candidate assessment and selection frameworks in e-recruitment system

E-recruitment systems support virtual interaction between experts and candidates to assess and select candidates based on the performance of candidates. However, security and privacy become critical challenges in such systems. Using an e-recruitment system, the employer invites experts to assess candidates eligible for a particular position or job, and based on the performance of the candidates, experts give their opinions. The employer fuses experts' opinions to decide on a candidate. Generally, experts provide scores based on the candidate's performance to represent their opinion. Candidates are selected based on the aggregate score they obtained from the experts. Experts may hesitate to give scores honestly if the privacy of their given scores is not preserved. Therefore, it is of utmost importance to preserve the privacy of scores given to candidates by the experts. Therefore, this paper proposes two privacy-preserving frameworks for candidate assessment and selection in an e-recruitment system using digital signatures, homomorphic encryption, and secure multi-party computation schemes to ensure data integrity and non-repudiation and preserve privacy. Experimental analysis exhibits that the proposed frameworks are practical and scalable and may be included in e-recruitment systems.