Reinforcement Learning-Based Sensitive Semantic Location Privacy Protection for VANETs

Location-based services(LBS)in vehicular ad hoc networks(VANETs)must protect users’privacy and address the threat of the exposure of sensitive locations during LBS requests.Users release not only their geographical but also semantic information of the visited places(e.g.,hospital).This sensitive information enables the inference attacker to exploit the users’preferences and life patterns.In this paper we propose a reinforcement learning(RL)based sensitive semantic location privacy protection scheme.This scheme uses the idea of differential privacy to randomize the released vehicle locations and adaptively selects the perturbation policy based on the sensitivity of the semantic location and the attack history.This scheme enables a vehicle to optimize the perturbation policy in terms of the privacy and the quality of service(QoS)loss without being aware of the current inference attack model in a dynamic privacy protection process.To solve the location protection problem with high-dimensional and continuous-valued perturbation policy variables,a deep deterministic policy gradientbased semantic location perturbation scheme(DSLP)is developed.The actor part is used to generate continuous privacy budget and perturbation angle,and the critic part is used to estimate the performance of the policy.Simulations demonstrate the DSLP-based scheme outperforms the benchmark schemes,which increases the privacy,reduces the QoS loss,and increases the utility of the vehicle.

A Location Privacy Preserving Solution to Resist Passive and Active Attacks in VANET

Existing location privacy- preserving methods, without a trusted third party, cannot resist conspiracy attacks and active attacks. This paper proposes a novel solution for location based service （LBS） in vehicular ad hoc network （VANET）. Firstly, the relationship among anonymity degree, expected company area and vehicle density is discussed. Then, a companion set F is set up by k neighbor vehicles. Based on secure multi-party computation, each vehicle in V can compute the centroid, not revealing its location to each other. The centroid as a cloaking location is sent to LBS provider （P） and P returns a point of interest （POI）. Due to a distributed secret sharing structure, P cannot obtain the positions of non-complicity vehicles by colluding with multiple internal vehicles. To detect fake data from dishonest vehicles, zero knowledge proof is adopted. Comparing with other related methods, our solution can resist passive and active attacks from internal and external nodes. It provides strong privacy protection for LBS in VANET.