The　proliferation　of　various　mobile　devices　equipped　with　cameras　results　in　an　exponential　growth　of　the　amount　of　images.　Recent　advances　in　the　deep　learning　with　convolutional　neural　networks　(CNN)　have　made　CNN　feature　extraction　become　an　effective　way　to　process　these　images.　However,　it　is　still　a　challenging　task　to　deploy　the　CNN　model　on　the　mobile　sensors,　which　are　typically　resource-constrained　in　terms　of　the　storage　space,　the　computing　capacity,　and　the　battery　life.　Although　cloud　computing　has　become　a　popular　solution,　data　security　and　response　latency　are　always　the　key　issues.　Therefore,　in　this　paper,　we　propose　a　novel　lightweight　framework　for　privacy-preserving　CNN　feature　extraction　for　mobile　sensing　based　on　edge　computing.　To　get　the　most　out　of　the　benefits　of　CNN　with　limited　physical　resources　on　the　mobile　sensors,　we　design　a　series　of　secure　interaction　protocols　and　utilize　two　edge　servers　to　collaboratively　perform　the　CNN　feature　extraction.　The　proposed　scheme　allows　us　to　significantly　reduce　the　latency　and　the　overhead　of　the　end　devices　while　preserving　privacy.　Through　theoretical　analysis　and　empirical　experiments,　we　demonstrate　the　security,　effectiveness,　and　efficiency　of　our　scheme.