Man-in-the-Middle Attack Resistant Secret Key Generation via Channel Randomization

TL;DR

This paper introduces a novel physical-layer key generation method using reconfigurable antennas to prevent man-in-the-middle attacks by disrupting the adversary's ability to correlate channel measurements, ensuring secure key agreement.

Contribution

The paper proposes a reconfigurable antenna-based channel randomization technique that enhances the security of physical-layer key generation against active MitM attacks.

Findings

The method effectively prevents adversaries from predicting secret key bits.

Experimental results show a significant reduction in attack success probability.

The approach maintains high key generation rates while improving security.

Abstract

Physical-layer based key generation schemes exploit the channel reciprocity for secret key extraction, which can achieve information-theoretic secrecy against eavesdroppers. Such methods, although practical, have been shown to be vulnerable against man-in-the-middle (MitM) attacks, where an active adversary, Mallory, can influence and infer part of the secret key generated between Alice and Bob by injecting her own packet upon observing highly correlated channel/RSS measurements from Alice and Bob. As all the channels remain stable within the channel coherence time, Mallory's injected packets cause Alice and Bob to measure similar RSS, which allows Mallory to successfully predict the derived key bits. To defend against such a MitM attack, we propose to utilize a reconfigurable antenna at one of the legitimate transceivers to proactively randomize the channel state across different channel probing rounds. The randomization of the antenna mode at every probing round breaks the temporal correlation of the channels from the adversary to the legitimate devices, while preserving the reciprocity of the channel between the latter. This prevents key injection from the adversary without affecting Alice and Bob's ability to measure common randomness. We theoretically analyze the security of the protocol and conduct extensive simulations and real-world experiments to evaluate its performance. Our results show that our approach eliminates the advantage of an active MitM attack by driving down the probability of successfully guessing bits of the secret key to a random guess.