Content Delivery Network (CDN) enhances Internet scalability and resilience against traditional Distributed Denial-of-Service (DDoS) attacks by deploying cached edge servers close to end-users. However, CDNs remain vulnerable to unique attack vectors, such as cache pollution attack (CPA). While existing research focuses on attack detection and mitigation, this paper investigates optimized CPA strategies from an adversarial perspective, specifically targeting CDN origin servers to bypass edge server defenses and amplify DDoS impacts. We analyze the attack mechanisms, evaluate performance degradation under varying CPA parameters, and quantify the scalability of this DDoS vector. Experimental results demonstrate that optimized CPA can exhaust origin server resources with fewer malicious requests, highlighting a pressing need for robust CDN architectural countermeasures.

The amount of content delivery traffic on the Internet has been increasing. To make Content Delivery Network (CDN) effective, it is necessary to clarify the attack methods targeting CDN cache servers and prevent them effectively. Therefore, in this paper, we evaluate and investigate the influence of attacks against CDN cache servers on the effect of increasing the response time. Many providers deploy multiple cache servers to prevent DDoS attacks and provide better services. In this paper, we investigate the impact of the two types of attacks, the Distributed Denial of Service (DDoS) attack and the Cache Pollution Attack (CPA), against the CDN cache servers. With the CDN model consisting of multiple cache servers, we evaluate the effect of the DDoS and CPA targeting CDN caches under different attacking scenarios, and we analyze the factors that affect the attack effect. Finally, we find several factors that affect the effect of the attacks, and CDN provider can focus on these factors to prevent the threat of cyber attacks on CDNs.