The growing prevalence of distributed denial of service (DDoS) attacks represents a serious threat to internet-connected systems. By overwhelming a target’s bandwidth or resources with traffic from multiple compromised devices, these attacks commonly disrupt websites and peer-to-peer platforms. As modern vehicles increasingly integrate full IP connectivity into their architecture, concerns are rising over their exposure to similar types of cyberattacks. Although no DDoS attacks on vehicles have been officially reported to date, the possibility remains a real and emerging risk for future transportation systems. Detecting and countering such attacks is therefore crucial to protect both passengers and the broader transportation infrastructure. As connected vehicles become more common, their role as internet-enabled, resource-rich mobile sensing platforms makes them vulnerable to cybersecurity threats, much like traditional computer networks. While these vehicles offer clear advantages in terms of convenience and traffic optimization, they also introduce new attack surfaces. Our research focuses on designing an intelligent detection system capable of reliably distinguishing between normal and malicious traffic. This would allow for early identification and rapid mitigation of DoS and DDoS attacks. In this study, we explore the application of deep learning methods to develop an effective, real-time defense mechanism tailored to the specific challenges of connected vehicle environments.