# Antonio Guimarães

Postdoctoral researcher at the IMDEA Software Institute, Madrid, Spain.

Antonio Guimarães is an applied cryptographer working on fully homomorphic encryption and its applications to privacy-preserving machine learning.

Links: [Email](mailto:antonio.guimaraes@imdea.org) · [CV](https://antonioguimaraes.org/cv/) · [Google Scholar](https://scholar.google.com/citations?user=UZzoYYgAAAAJ) · [GitHub](https://github.com/antoniocgj) · [ORCID](https://orcid.org/0000-0001-5110-6639) · [DBLP](https://dblp.org/pid/245/2520.html) · [ePrint](https://eprint.iacr.org/search?q=Guimar%C3%A3es)

## Research

Fully homomorphic encryption (FHE) enables arbitrary computation directly over encrypted data. In practice, however, it faces many limitations that restrict its application in realistic scenarios. My work addresses them.

- **Verifiable FHE**: In FHE, one typically considers an idealized model where adversaries are honest-but-curious (they try to learn the data but follow the protocol). Real-world adversaries may be malicious: they can return incorrect results and use them to mount reaction attacks that recover the data or the secret key. [Verifiable FHE](https://antonioguimaraes.org/publications/?topic=verifiable) lets the client check that the intended computation was performed before decrypting. My work was the first to make this practical for modern FHE schemes, both [exact](https://antonioguimaraes.org/publications/?topic=verifiable&tag=exact-vfhe) and [approximate](https://antonioguimaraes.org/publications/?topic=verifiable&tag=approximate-vfhe).
- **FHE-based MPC**: FHE enables multi-party computation (MPC) with communication independent of the function being computed. Two techniques help make it practical: [threshold FHE](https://antonioguimaraes.org/publications/?topic=threshold), which distributes the secret key among the parties, and [hybrid homomorphic encryption (HHE)](https://antonioguimaraes.org/publications/?topic=transciphering), which keeps communication concretely low by replacing large FHE ciphertexts with short symmetric ones. I work on both, including threshold decryption that needs no coordination.
- **Practical performance**: Computing over encrypted data may be orders of magnitude slower than in the clear, which has restricted FHE to small-scale applications. I address this at two levels. At the primitive level, I design new algorithms for [bootstrapping](https://antonioguimaraes.org/publications/?topic=bootstrapping), which dominates this cost. At the application level, I develop efficient methods for [training and inference of machine-learning models](https://antonioguimaraes.org/publications/?topic=ml) over encrypted data. My goal is FHE fast and scalable enough for the models used in practice.

## Research topics

Homomorphic encryption, Fast bootstrapping, Verifiable FHE, Transciphering / HHE, Threshold FHE, Post-quantum cryptography, Efficient implementation, Privacy-preserving ML, Side channels, HPC & cloud, Education

## Publications

- 2026 · [TUTTI: Parallel CKKS Bootstrapping in under 3 ms on CPU](https://antonioguimaraes.org/publications/tutti.md) — Robin Köstler, Antonio Guimarães. *arXiv:2611.12854*.
- 2027 · [Tulva: Practical Asynchronous Threshold FHE](https://antonioguimaraes.org/publications/tulva.md) — Valerio Cini, Antonio Guimarães, Russell W. F. Lai, Michał Osadnik, Ivy K. Y. Woo. *IEEE S&P 2027*.
- 2026 · [Batch, Pack, and Prove: More Efficient Verifiable Computation for CKKS](https://antonioguimaraes.org/publications/batch-pack-prove.md) — Ignacio Cascudo, Anamaria Costache, Daniele Cozzo, Dario Fiore, Antonio Guimarães, Eduardo Soria-Vazquez. *ASIACRYPT 2026*.
- 2026 · [PETCHA: Post-quantum Efficient Transciphering with ChaCha](https://antonioguimaraes.org/publications/petcha.md) — Antonio Guimarães, Gabriela M. Jacob, Hilder V. L. Pereira. *PQCrypto 2026*.
- 2025 · [Nostalgia Cipher: Can Filtered LFSRs Be Secure Again? An Application to Hybrid Homomorphic Encryption with Sub-50 ms Latency](https://antonioguimaraes.org/publications/nostalgia-cipher.md) — Nabil Chacal, Antonio Guimarães, Ange Martinelli, Pierrick Méaux, Romain Poussier. *ToSC 2025*.
- 2025 · [Fast amortized bootstrapping with small keys and polynomial noise overhead](https://antonioguimaraes.org/publications/fast-amortized-bootstrapping.md) — Antonio Guimarães, Hilder V. L. Pereira. *CCS 2025*.
- 2025 · [Verifiable Computation for Approximate Homomorphic Encryption Schemes](https://antonioguimaraes.org/publications/verifiable-approximate-he.md) — Ignacio Cascudo, Anamaria Costache, Daniele Cozzo, Dario Fiore, Antonio Guimarães, Eduardo Soria-Vazquez. *CRYPTO 2025*.
- 2025 · [Homomorphic WiSARDs: Efficient Weightless Neural Network training over encrypted data](https://antonioguimaraes.org/publications/homomorphic-wisards.md) — Leonardo Neumann, Antonio Guimarães, Diego F. Aranha, Edson Borin. *ACNS 2025*.
- 2025 · [RISC-V Assembly Learning Environment: An extensible web-based platform](https://antonioguimaraes.org/publications/riscv-ale.md) — João Seródio, Antonio Guimarães, Edson Borin. *WCAE 2025*.
- 2025 · [Secure and efficient transciphering for FHE-based MPC](https://antonioguimaraes.org/publications/transciphering-fhe-mpc.md) — Diego F. Aranha, Antonio Guimarães, Clément Hoffmann, Pierrick Méaux. *TCHES 2025*.
- 2024 · [HELIOPOLIS: Verifiable Computation over Homomorphically Encrypted Data from Interactive Oracle Proofs is Practical](https://antonioguimaraes.org/publications/heliopolis.md) — Diego F. Aranha, Anamaria Costache, Antonio Guimarães, Eduardo Soria-Vazquez. *ASIACRYPT 2024*.
- 2024 · [MOSFHET: Optimized Software for FHE over the Torus](https://antonioguimaraes.org/publications/mosfhet.md) — Antonio Guimarães, Edson Borin, Diego F. Aranha. *JCEN 2024*.
- 2023 · [Amortized Bootstrapping Revisited: Simpler, Asymptotically-faster, Implemented](https://antonioguimaraes.org/publications/amortized-bootstrapping-revisited.md) — Antonio Guimarães, Hilder V. L. Pereira, Barry van Leeuwen. *ASIACRYPT 2023*.
- 2022 · [Homomorphic evaluation of large look-up tables for inference on human genome data in the cloud](https://antonioguimaraes.org/publications/homomorphic-lut-genome.md) — Antonio Guimarães, Leonardo Neumann, Fernanda A. Andaló, Diego F. Aranha, Edson Borin. *WCC 2022*.
- 2021 · [Revisiting the functional bootstrap in TFHE](https://antonioguimaraes.org/publications/functional-bootstrap-tfhe.md) — Antonio Guimarães, Edson Borin, Diego F. Aranha. *TCHES 2021*.
- 2021 · [High-performance IO for seismic processing on the cloud](https://antonioguimaraes.org/publications/seismic-io-cloud.md) — Antonio Guimarães, Luis Lacalle, Charles B. Rodamilans, Edson Borin. *CCPE 2021*.
- 2020 · [Efficient and secure software implementations of Fantomas](https://antonioguimaraes.org/publications/fantomas.md) — Rafael J. Cruz, Antonio Guimarães, Diego F. Aranha. *JCEN 2020*.
- 2019 · [Optimized implementation of QC-MDPC code-based cryptography](https://antonioguimaraes.org/publications/qc-mdpc-optimized.md) — Antonio Guimarães, Diego F. Aranha, Edson Borin. *CCPE 2019*.
- 2019 · [Introducing Arithmetic Failures to Accelerate QC-MDPC Code-Based Cryptography](https://antonioguimaraes.org/publications/qc-mdpc-arithmetic-failures.md) — Antonio Guimarães, Edson Borin, Diego F. Aranha. *CBC 2019*.
- 2017 · [Optimizing the Decoding Process of a Post-Quantum Cryptographic Algorithm](https://antonioguimaraes.org/publications/qc-mdpc-decoding.md) — Antonio Guimarães, Diego F. Aranha, Edson Borin. *WSCAD 2017*.

## News

- Nov 9, 2026: TUTTI, parallel CKKS bootstrapping in under 3 ms on CPU, is on arXiv and ePrint.
- Oct 16, 2026: Tulva: Practical Asynchronous Threshold FHE accepted at IEEE S&P 2027.
- Aug 15, 2026: Batch, Pack, and Prove: More Efficient Verifiable Computation for CKKS accepted at ASIACRYPT 2026.
- Jan 23, 2026: PETCHA, post-quantum transciphering with ChaCha, is on ePrint and accepted at PQCrypto 2026.
- Nov 23, 2025: Nostalgia Cipher accepted at IACR ToSC 2025: filtered LFSRs for hybrid homomorphic encryption with sub-50 ms latency.
- Oct 2025: Awarded a Juan de la Cierva postdoctoral fellowship by the Spanish Ministry of Science.
- Oct 13, 2025: Presented Fast amortized bootstrapping with small keys at ACM CCS 2025 in Taipei.
- Aug 17, 2025: Verifiable Computation for Approximate Homomorphic Encryption Schemes presented at CRYPTO 2025.
- Jun 23, 2025: Homomorphic WiSARDs, encrypted training of weightless neural networks, presented at ACNS 2025.
- Jun 5, 2025: Secure and efficient transciphering for FHE-based MPC published in IACR TCHES 2025(3).

Full site: https://antonioguimaraes.org/ · Markdown index: https://antonioguimaraes.org/llms.txt