Pith. sign in

REVIEW 4 cited by

Encryption-Friendly LLM Architecture

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.02486 v2 pith:YVPBW7ZB submitted 2024-10-03 cs.CR cs.LG

Donghwan Rho , Taeseong Kim , Minje Park , Jung Woo Kim , Hyunsik Chae , Ernest K. Ryu , Jung Hee Cheon This is my paper · ORCID
classification cs.CRcs.LG
keywords fine-tuningarchitecturecomputationalinferencellmsmodelspersonalizedprivacy-preserving
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) offer personalized responses based on user interactions, but this use case raises serious privacy concerns. Homomorphic encryption (HE) is a cryptographic protocol supporting arithmetic computations in encrypted states and provides a potential solution for privacy-preserving machine learning (PPML). However, the computational intensity of transformers poses challenges for applying HE to LLMs. In this work, we propose a modified HE-friendly transformer architecture with an emphasis on inference following personalized (private) fine-tuning. Utilizing LoRA fine-tuning and Gaussian kernels, we achieve significant computational speedups -- 6.94x for fine-tuning and 2.3x for inference -- while maintaining performance comparable to plaintext models. Our findings provide a viable proof of concept for offering privacy-preserving LLM services in areas where data protection is crucial. Our code is available on GitHub.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense

    cs.CR 2025-02 conditional novelty 7.0 of 10

    Activation approximations used for faster LLM inference can dramatically increase jailbreak success rates on aligned models, and the paper's QuadA training method restores robust refusal.

  2. ENSI: Efficient Non-Interactive Secure Inference for Large Language Models

    cs.CR 2025-09 conditional novelty 6.0 of 10

    ENSI performs secure, non-interactive LLM inference by co-designing CKKS homomorphic encryption with BitNet's ternary weights, achieving up to 8x faster matrix multiplication and 2.6x faster softmax than prior work.

  3. Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques

    cs.LG 2025-06 unverdicted novelty 4.0 of 10

    A survey of LLM routing and hierarchical inference techniques that proposes an unvalidated unified evaluation metric called the Inference Efficiency Score.

  4. SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

    cs.CR 2025-06 conditional novelty 3.0 of 10

    A systematization-of-knowledge survey that categorizes LLM privacy risks into training data, prompts, outputs, and agents, and reviews limitations of current mitigations.

Pith tools