Star enables private and scalable internet rate limiting with trusted hardware
STAR: Scalable TEE-based Anonymous Rate-limiter
Cryptography and Security
Summary
Internet services often need to limit how often users make requests to avoid attacks, but tracking users can hurt their privacy. The authors present STAR, a system that uses special secure hardware inside servers to check user limits without revealing who they are. They solve technical challenges to make the system fast and safe, even if some parts try to sneak information from memory access patterns. Their tests show STAR can handle many requests quickly while protecting users' privacy.
What this means in practice
- •For internet service providers: Implement privacy-preserving rate limits to block attack traffic without identifying users directly.
- •For cloud service operators: Distribute client request authentication efficiently across servers using trusted hardware to maintain privacy.
Authors
Kosei Akama, Yoshimichi Nakatsuka, Koichi Moriyama, Keisuke Uehara
Abstract
Protecting Internet services from attacks such as TLS/HTTP floods requires rate limiting, yet identifying users to enforce these limits can compromise their privacy. Anonymous rate limiting promises to reconcile these goals, but existing schemes either struggle to scale or assume that services and authorities do not collude. We present STAR, which uses server-side trusted execution environments (TEEs) to overcome these limitations. By enabling lightweight cryptographic operations, TEEs make authentication efficient, but introduce a privacy challenge: malicious services can observe memory-access patterns to infer user secrets. We address this threat through countermeasures against secret-dependent memory accesses and assess our implementation using dynamic analysis. To extend these efficiency gains across servers, we also design a secure sharding mechanism that distributes client requests. We demonstrate that strong privacy guarantees can coexist with efficient authentication at scale; STAR processes authentication requests in tens of microseconds and handles approximately 13.9K requests per second per CPU core.