analiza aiqbench
This paper applies CKKS homomorphic encryption to ML inference, so a health-misinformation classifier and a semantic retriever can run on encrypted text without exposing user queries. The reported accuracy (0.971) and retrieval correlation (0.8691 on STS-B) are close to plaintext performance, but the ciphertext retrieval still takes about 5 seconds per query over 7,128 items, so practical deployment depends on latency and infrastructure costs. Readers interested in privacy-preserving ML should look at the SIMD packing results, which cut latency and communication overhead sharply.
Privacy-Preserving Text Inference for Health-Misinformation Classification and Semantic Retrieval
arXiv:2610.20796v1 Announce Type: cross Abstract: Health-misinformation analysis presents a dual challenge: misleading claims can affect public well-being, while systems designed to detect them may expose sensitive user-submitted text. This motivates privacy-preserving inference for public-health applications in which user queries may contain confidential medical information and trained models and reference databases are maintained on organizational servers. We design a privacy-preserving text inference framework based on CKKS homomorphic encryption for health-misinformation classification and semantic retrieval. The classification pipeline fuses BioBERT embeddings, PCA-reduced MPNet embeddings, and SVD-reduced TF-IDF features, while the retrieval pipeline combines MPNet embeddings with ISCC-SCT semantic fingerprints through late fusion. We evaluate predictive performance and benchmark plaintext versus ciphertext-based execution. The hybrid classifier achieved an accuracy of 0.971 and a macro-F1 score of 0.950, with identical reported metrics under plaintext and ciphertext-based inference. The hybrid late-fusion similarity model achieved a Pearson correlation of 0.8691 with human sentence-pair similarity scores on STS-B. For ciphertext-based retrieval, we evaluated naive and optimized implementations. The optimized implementation uses CKKS single instruction, multiple data (SIMD) packing to compute and return multiple similarity scores together, reducing single-query latency over 7,128 indexed items from 222.028 to 5.168 seconds and communication overhead from 6.11 GB to 2.13 MB. These findings demonstrate the technical feasibility of privacy-preserving text inference for health-misinformation applications and characterize its predictive utility and efficiency trade-offs.
Abstract:Health-misinformation analysis presents a dual challenge: misleading claims can affect public well-being, while systems designed to detect them may expose sensitive user-submitted text. This motivates privacy-preserving inference for public-health applications in which user queries may contain confidential medical information and trained models and reference databases are maintained on organizational servers. We design a privacy-preserving text inference framework based on CKKS homomorphic encryption for health-misinformation classification and semantic retrieval. The classification pipeline fuses BioBERT embeddings, PCA-reduced MPNet embeddings, and SVD-reduced TF-IDF features, while the retrieval pipeline combines MPNet embeddings with ISCC-SCT semantic fingerprints through late fusion. We evaluate predictive performance and benchmark plaintext versus ciphertext-based execution. The hybrid classifier achieved an accuracy of 0.971 and a macro-F1 score of 0.950, with identical reported metrics under plaintext and ciphertext-based inference. The hybrid late-fusion similarity model achieved a Pearson correlation of 0.8691 with human sentence-pair similarity scores on STS-B. For ciphertext-based retrieval, we evaluated naive and optimized implementations. The optimized implementation uses CKKS single instruction, multiple data (SIMD) packing to compute and return multiple similarity scores together, reducing single-query latency over 7,128 indexed items from 222.028 to 5.168 seconds and communication overhead from 6.11 GB to 2.13 MB. These findings demonstrate the technical feasibility of privacy-preserving text inference for health-misinformation applications and characterize its predictive utility and efficiency trade-offs.
Cryptography and Security (cs.CR); Machine Learning (cs.LG)
arXiv:2610.20796 [cs.CR]
(or arXiv:2610.20796v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2610.20796 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 314 cuvinte
Subiecte conexe
[AINews] not much happened today
Latent Space · 18 sept. 2026
Biomedical Imaging's Real Bottleneck Is the Data, Not the Model
Databricks · 8 oct. 2026
Building Trustworthy Snowflake AI Agents with Semantic Governance
Analytics Vidhya · 8 aug. 2026
PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration
arXiv · 6 aug. 2026