International Association
for Cryptologic Research

We present the first specification-compliant constant-time FPGA implementation of the Classic McEliece cryptosystem from the third-round of NIST’s Post-Quantum Cryptography standardization process. In particular, we present the first complete implementation including encapsulation and decapsulation modules as well as key generation with seed expansion. All the hardware modules are parametrizable, at compile time, with security level and performance parameters. As the most time consuming operation of Classic McEliece is the systemization of the public key matrix during key generation, we present and evaluate three new algorithms that can be used for systemization while complying with the specification: hybrid early-abort systemizer (HEA), single-pass early-abort systemizer (SPEA), and dual-pass earlyabort systemizer (DPEA). All of the designs outperform the prior systemizer designs for Classic McEliece by 2.2x to 2.6x in average runtime and by 1.7x to 2.4x in time-area efficiency. We show that our complete Classic McEliece design for example can perform key generation in 5.2 ms to 20 ms, encapsulation in 0.1 ms to 0.5 ms, and decapsulation in 0.7 ms to 1.5 ms for all security levels on an Xlilinx Artix 7 FPGA. The performance can be increased even further at the cost of resources by increasing the level of parallelization using the performance parameters of our design.

We present and evaluate a custom extension to the RISC-V instruction set for finite field arithmetic. The result serves as a very compact approach to software-hardware co-design of PQC implementations in the context of small embedded processors such as smartcards. The extension provides instructions that implement finite field operations with subsequent reduction of the result. As small finite fields are used in various PQC schemes, such instructions can provide a considerable speedup for an otherwise software-based implementation. Furthermore, we create a prototype implementation of the presented instructions for the extendable VexRiscv core, integrate the result into a chip design, and evaluate the design on two different FPGA platforms. The effectiveness of the extension is evaluated by using the instructions to optimize the Kyber and NewHope key-encapsulation schemes. To that end, we also present an optimized software implementation for the standard RISC-V instruction set for the polynomial arithmetic underlying those schemes, which serves as basis for comparison. Both variants are tuned on an assembler level to optimally use the processor pipelines of contemporary RISC-V CPUs. The result shows a speedup for the polynomial arithmetic of up to 85% over the basic software implementation. Using the custom instructions drastically reduces the code and data size of the implementation without introducing runtime-performance penalties at a small cost in circuit size. When used in the selected schemes, the custom instructions can be used to replace a full general purpose multiplier to achieve very compact implementations.

This paper presents an attack based on side-channel information and information set decoding (ISD) on the code-based Niederreiter cryptosystem and an evaluation of the practicality of the attack using an electromagnetic side channel. We start by directly adapting the timing side-channel plaintext-recovery attack by Shoufan et al. from 2010 to the constant-time implementation of the Niederreiter cryptosystem as used in the official FPGA-implementation of the NIST finalist “Classic McEliece”. We then enhance our attack using ISD and a new technique that we call iterative chunking to further significantly reduce the number of required side-channel measurements. We theoretically show that our attack improvements have a significant impact on reducing the number of required side-channel measurements. For example, for the 256-bit security parameter set kem/mceliece6960119 of “Classic McEliece”, we improve the basic attack that requires 5415 measurements to less than 562 measurements on average to mount a successful plaintext-recovery attack. Further reductions can be achieved at the price of increasing the cost of the ISD computations. We confirm our findings by practically mounting the attack on the official FPGA-implementation of “Classic McEliece” for all proposed parameter sets.

This paper proposes two different methods to perform NTT-based polynomial multiplication in polynomial rings that do not naturally support such a multiplication. We demonstrate these methods on the NTRU Prime key-encapsulation mechanism (KEM) proposed by Bernstein, Chuengsatiansup, Lange, and Vredendaal, which uses a polynomial ring that is, by design, not amenable to use with NTT. One of our approaches is using Good’s trick and focuses on speed and supporting more than one parameter set with a single implementation. The other approach is using a mixed radix NTT and focuses on the use of smaller multipliers and less memory. On a ARM Cortex-M4 microcontroller, we show that our three NTT-based implementations, one based on Good’s trick and two mixed radix NTTs, provide between 32% and 17% faster polynomial multiplication. For the parameter-set ntrulpr761, this results in between 16% and 9% faster total operations (sum of key generation, encapsulation, and decapsulation) and requires between 15% and 39% less memory than the current state-of-the-art NTRU Prime implementation on this platform, which is using Toom-Cook-based polynomial multiplication.

This paper presents a post-quantum secure, efficient, and tunable FPGA implementation of the key-generation algorithm for the Niederreiter cryptosystem using binary Goppa codes. Our key-generator implementation requires as few as 896,052 cycles to produce both public and private portions of a key, and can achieve an estimated frequency Fmax of over 240 MHz when synthesized for Stratix V FPGAs. To the best of our knowledge, this work is the first hardware-based implementation that works with parameters equivalent to, or exceeding, the recommended 128-bit “post-quantum security” level. The key generator can produce a key pair for parameters $$m=13$$, $$t=119$$, and $$n=6960$$ in only 3.7 ms when no systemization failure occurs, and in $$3.5 \cdot 3.7$$ ms on average. To achieve such performance, we implemented an optimized and parameterized Gaussian systemizer for matrix systemization, which works for any large-sized matrix over any binary field $$\text {GF}(2^m)$$. Our work also presents an FPGA-based implementation of the Gao-Mateer additive FFT, which only takes about 1000 clock cycles to finish the evaluation of a degree-119 polynomial at $$2^{13}$$ data points. The Verilog HDL code of our key generator is parameterized and partly code-generated using Python and Sage. It can be synthesized for different parameters, not just the ones shown in this paper. We tested the design using a Sage reference implementation, iVerilog simulation, and on real FPGA hardware.