Abstract

Many existing peer-to-peer content distribution networks (CDNs) such as Na Kika, CoralCDN, and CoDeeN are deployed on PlanetLab, a relatively trusted environment. But scaling them beyond this trusted boundary requires protecting against content corruption by untrusted replicas. This paper presents Repeat and Compare, a system for ensuring content integrity in untrusted peer-to-peer CDNs even when replicas dynamically generate content. Repeat and Compare detects misbehaving replicas through attestation records and sampled repeated execution. Attestation records, which are included in responses, cryptographically bind replicas to their code, inputs, and dynamically generated output. Clients then forward a fraction of these records to randomly selected replicas acting as verifiers. Verifiers, in turn, reliably identify misbehaving replicas by locally repeating response generation and comparing their results with the attestation records. We have implemented our system on top of Na Kika. We quantify its detection guarantees through probabilistic analysis and show through simulations that a small sample of forwarded records is sufficient to effectively and promptly cleanse a CDN, even if large fractions of replicas or verifiers are misbehaving. 1

Citations