mlsanityData to 13 Oct 2026

Balancing Privacy and Efficiency: Music Information Retrieval via Additive Homomorphic Encryption

arXiv 2508.07044 ↗First posted 9 Aug 2025cs.DB cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern music retrieval runs on vector embeddings, and once these embeddings are shared for search or matching they can be copied, probed, or used to train generative models. Fully homomorphic encryption can compute on them but is impractical at scale because of ciphertext--ciphertext multiplication and bootstrapping. We observe that when only one operand is encrypted, the query or the database, similarity search reduces to ciphertext addition and ciphertext--plaintext multiplication, which additive homomorphic encryption supports cheaply (through Paillier, or CKKS restricted to additive operations). Building on this observation, we (i) implement two music-specific inference attacks and quantify the privacy--utility tradeoff of provable mitigations, (ii) introduce structure-aware additive primitives with learned per-block weighting at no extra cryptographic cost, and (iii) show across four audio datasets that additive search preserves nearest-neighbor rankings exactly while avoiding the ciphertext--ciphertext multiplication and bootstrapping of full-depth FHE and scaling far better in embedding dimension than a true-additive Paillier baseline.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 23 of its 80 references that are in the map. First posted on arXiv 9 Aug 2025.

Builds on

23 of 80 references.

References · 23

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,870
  2. 2016Deep Learning with Differential Privacycited by 2,718
  3. 2017Billion-scale similarity search with GPUscited by 2,490
  4. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,313
  5. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 857
  6. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 713
  7. 2016CNN Architectures for Large-Scale Audio Classificationcited by 702
  8. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 613
  9. 2020Jukebox: A Generative Model for Musiccited by 537
  10. 2023MusicLM: Generating Music From Textcited by 445
  11. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 218
  12. 2016FMA: A Dataset For Music Analysiscited by 207
11 more
  1. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  2. 2023MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Trainingcited by 177
  3. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  4. 2021TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryptioncited by 52
  5. 2017Deep Learning Techniques for Music Generation -- A Surveycited by 49
  6. 2020PiRhDy: Learning Pitch-, Rhythm-, and Dynamics-aware Embeddings for Symbolic Musiccited by 24
  7. 2019SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Searchcited by 12
  8. 2019Accurate and Scalable Version Identification Using Musically-Motivated Embeddingscited by 7
  9. 2013Secure k-Nearest Neighbor Query over Encrypted Data in Outsourced Environmentscited by 3
  10. 2021Prism: Private Verifiable Set Computation over Multi-Owner Outsourced Databasescited by 3
  11. 2025A Note on Efficient Privacy-Preserving Similarity Search for Encrypted Vectorscited by 1

Built on by

Not cited yet.