Full-PQC TLS 1.3 beats classical handshakes on constrained devices
Original title: Testing TLS 1.3 PQC on constrained devices and microcontrollers
On wolfSSL, ML-KEM-512 with ML-DSA-44 was 41% faster than X25519 with RSA-PSS on the Pico W and 8.9 times faster on the ESP32.
A paper benchmarks 36 TLS 1.3 algorithm pairings with wolfSSL on a Raspberry Pi Pico W, Pico 2 W, ESP32, and Raspberry Pi Zero, measuring handshake latency and energy. On capable hardware the choices were similar, but on IoT-class devices full post-quantum ML-KEM-512 plus ML-DSA-44 was faster and often more energy-efficient than classical or hybrid pairings. The draft X25519 plus ML-KEM-768 hybrid costs about both components combined, and ML-DSA signing time varies.
- Governments cited have PQC migration deadlines from 2028 to 2035.
- The matrix pairs ML-KEM-512/768/1024 and X25519 or P-256 with ML-DSA, Ed25519, ECDSA, and RSA-PSS.
- Best full-PQC was up to 2.12 times as energy-efficient on the Pico W, depending on authentication.
- Pure ML-KEM is more practical where Curve25519 assembly support is missing.
- Vendors
- wolfSSL
From the original article
1 min read at arxiv.orgThe UK, EU and US governments have set timelines for post-quantum cryptography migration of critical systems, with deadlines ranging from 2028 to 2035. This paper focuses on IoT-class devices and microcontrollers and the viability of using PQC to connect these devices in secure TLS 1. 3 connections.
By Olivier Gillot · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.