Federated　learning　is　a　privacy-preserving　machine　learning　paradigm　consisting　of　local　model　training,　global　model　aggregation,　and　global　model　distribution.　Recent　research　found　that　model　aggregation　can　reveal　the　participants＇　privacy.　To　preserve　the　participants＇　privacy,　multi-party　computation-based　secure　aggregation　is　used　in　federated　learning　with　mobile　device　participants.　The　character　of　the　mobile　device　requires　that　secure　aggregation　can　be　efficient　in　computation　and　robust　to　the　dropout.　However,　prior　works　need　multi　rounds,　increase　computation　cost　related　to　the　dropped　participants,　and　fails　to　resist　quantum　attacks.　To　solve　these　issues,　we　propose　a　3-round　post-quantum　secure　protocol　for　federated　learning.　In　the　proposed　protocol,　single-masking　generated　by　homomorphic　Pseudorandom　Generator　based　on　learning　with　round　encrypts　single　user＇s　model.　After　all　the　encrypted　models　are　aggregated　fast,　additively　homomorphic　decryption　based　on　Shamir　secret　share　guarantee　the　robustness　and　performance　induced　by　the　dropped　participants.　All　message　exchange　is　based　on　a　post-quantum　secure　channel　constructed　with　the　first　post-quantum　cryptography　standard,　Kyber　KEM.　In　post-quantum　security,　security　analysis　demonstrates　that　the　proposed　protocol　can　preserve　privacy　under　the　sem-honest　adversaries　setting,　and　the　experimental　results　show　higher　running　time　efficiency.　©　2022　ACM.