Nowadays, a numerous fatalities have resulted from road damage. Research into road damage detection, particularly the detection and notification of hazardous road damage is essential for enhancing the traffic security. Existing road damage identification schemes often process data in the cloud, but they are unable to warn users on time on account of lengthy latency. Although newer edge computing strategies reduce this issue owing to the limited communication range of edges, the users can only get notifications about potentially harmful road damage within a small radius. Besides, untrusted nodes may misuse the sensitive information of users. Therefore, in this manuscript, a Privacy-preserving Dual Interactive Wasserstein Generative Adversarial Network is proposed for Cloud-Based Road Condition Monitoring in VANETs (PP-DIWGAN-C-RCM-VANET). Here, local models and global models are the two types of cloud detection models are considered. In which, the local models acquire knowledge from cloud-based data, whereas global models support local models' learning by combining local models. The intention of the proposed approach is “to detect the smart hazardous road condition”. The local model recognizes dangerous roads, and also categorized into 3 levels: low, middle, and high, these are based on information gathered about the state of the roads. From the road crack dataset, it is categorized into crack, normal and pothole. DIWGAN secures secrecy from unreliable clouds, but it is still significant danger of privacy leaking from unreliable edges. To ensure privacy, users must erase all data before transmitting it to the edges, here the user indicates the owner of the vehicle. Therefore, a new privacy preserving method called Fractional Discrete Meixner Moments Encryption (FDMME) is taken into account to fulfill this requirement. For real time dataset, the proposed method achieves better accuracy 27.5%, 10.32% and 16.65%, better f-score 30.93%, 11.14% and 15.3% compared with existing methods.