用加法同态加密实现高效音乐检索，兼顾隐私与性能。
Balancing Privacy and Efficiency: Music Information Retrieval via Additive Homomorphic Encryption
- 仅加密查询或数据库，用加法同态支持快速相似性搜索。
- 在4个音频数据集上保持最近邻排序完全一致，且扩展性优于传统方案。
- 新增结构感知加权机制，无额外加密开销，适合实际部署。
现代音乐检索依赖向量嵌入，但共享嵌入后易被复制、探测或用于生成模型训练。全同态加密虽可计算但因密文-密文乘法和引导操作难以规模化。我们观察到，当仅一方（查询或数据库）加密时，相似性搜索退化为密文加法与密文-明文乘法，可由加法同态加密高效支持（如Paillier或限制为加法的CKKS）。基于此，我们：(i) 实现两种针对音乐的推断攻击并量化可证明缓解方案的隐私-效用权衡；(ii) 提出结构感知的加法原语，通过学习块级权重实现，无需额外加密成本；(iii) 在四个音频数据集上验证，加法搜索能精确保留最近邻排序，避免全深度FHE中的密文-密文乘法与引导操作，在嵌入维度上扩展性远超真正的加法Paillier基线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。