Memory-Efficient Designs for Word-Wise Universal Fully Homomorphic Encryption
BXT framework mitigates FHE memory bottlenecks via ciphertext compression, serialization, delayed seeding, and digit pruning, achieving up to 3.8x CNN inference speedup.
A new paper proposes BXT, an optimization framework for word-wise Universal Fully Homomorphic Encryption that targets the memory bottleneck rather than compute. It combines four techniques: ciphertext compression via seed regeneration, bit-packed ciphertext serialization for L2-to-L1 transfers, delayed PRNG-heavy offline seed generation across aggregated operations, and fault-aware ciphertext digit pruning. On CNN inference, the BXT-CSO50 configuration achieves up to 3.8x speedup over a 100x GPU baseline with under 1% accuracy loss at 50% comparison precision.
- FHE magnifies data sizes by orders of magnitude, shifting bottlenecks from compute to memory.
- Four techniques reduce ciphertext memory traffic and offline PRNG overhead.
- Tags
- ciphertext-compressioncryptographyhomomorphic-encryptionperformance-optimizationprivacy-preserving-computation
- Products
- BXT
From the original article
1 min read at arxiv.orgFully Homomorphic Encryption (FHE) enables computation on encrypted data, preserving privacy throughout analysis. While its privacy is very strong, FHE is much slower to execute than the original computation.
By Ardhi Wiratama Baskara Yudha · 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.