With　the　rapid　development　of　IoT　and　fog　computing,　mobile　devices　can　offload　computing　tasks　into　the　fog　layer　to　reduce　energy　consumption　and　transmission　delay.　However,　the　communication　between　fog　nodes　and　end　users　is　vulnerable　to　malicious　jamming　attacks.　In　this　paper,　we　propose　a　reinforcement　learning-based　computation　offloading　strategy　to　choose　fog　nodes,　offloading　rate,　and　transmit　power　to　address　jamming　attacks　and　interference　problems.　We　use　dueling　deep　Q-network　to　accelerate　the　learning　speed　in　the　system,　which　can　effectively　determine　the　offloading　strategy.　The　simulation　results　show　that　this　scheme　based　on　DDQN　is　better　than　DQN　and　Q-learning　in　terms　of　computational　latency　and　energy　consumption.　©　2022　ACM.