# Practical and Provably Secure Onion Routing

## TL;DR

This paper introduces practical, provably secure onion routing protocols that ensure anonymity against various adversaries, with efficient security parameters and independent path selection similar to Tor.

## Contribution

It presents the first practical and provably secure onion routing protocols with differential privacy guarantees against active adversaries.

## Key findings

- Protocols operate in $O( ext{log}^2 \\lambda)$ rounds.
- Require each participant to send $O( ext{log}^4 \\lambda)$ onions per round.
- Achieve security under standard adversary models.

## Abstract

In an onion routing protocol, messages travel through several intermediaries before arriving at their destinations, they are wrapped in layers of encryption (hence they are called "onions"). The goal is to make it hard to establish who sent the message. It is a practical and widespread tool for creating anonymous channels. For the standard adversary models -- network, passive, and active -- we present practical and provably secure onion routing protocols. Akin to Tor, in our protocols each party independently chooses the routing paths for his onions. For security parameter $\lambda$, our differentially private solution for the active adversary takes $O(\log^2\lambda)$ rounds and requires every participant to transmit $O(\log^{4} \lambda)$ onions in every round.