Modern machine learning systems increasingly rely on sensitive data, creating significant privacy, security, and regulatory risks that existing privacy-preserving machine learning (ppML) techniques, such as Differential Privacy (DP) and Homomorphic Encryption (HE), address only at the cost of degraded performance, increased complexity, or prohibitive computational overhead. This paper introduces Informationally Compressive Anonymization (ICA) and the VEIL architecture, a privacy-preserving ML framework that achieves strong privacy guarantees through architectural and mathematical design rather than noise injection or cryptography. ICA embeds a supervised, multi-objective encoder within a trusted Source Environment to transform raw inputs into low-dimensional, task-aligned latent representations, ensuring that only irreversibly anonymized vectors are exported to untrusted training and inference environments. The paper rigorously proves that these encodings are structurally non-invertible using topological and information-theoretic arguments, showing that inversion is logically impossible, even under idealized attacker assumptions, and that, in realistic deployments, the attacker conditional entropy over the original data diverges, driving reconstruction probability to zero. Unlike prior autoencoder-based ppML approaches, ICA preserves predictive utility by aligning representation learning with downstream supervised objectives, enabling low-latency, high-performance ML without gradient clipping, noise budgets, or encryption at inference time. The VEIL architecture enforces strict trust boundaries, supports scalable multi-region deployment, and naturally aligns with privacy-by-design regulatory frameworks, establishing a new foundation for enterprise ML that is secure, performant, and safe by construction, even in the face of post-quantum threats.

翻译：现代机器学习系统日益依赖敏感数据，这引发了重大的隐私、安全及合规风险。现有的隐私保护机器学习（ppML）技术，如差分隐私（DP）和同态加密（HE），虽能应对上述风险，却以性能退化、复杂度增加或高昂计算开销为代价。本文提出信息压缩匿名化（ICA）与VEIL架构——一种通过架构与数学设计（而非噪声注入或密码学）实现强隐私保障的隐私保护机器学习框架。ICA在可信源环境中嵌入有监督多目标编码器，将原始输入转化为低维、任务对齐的隐空间表征，确保仅将不可逆匿名化的向量导出至不可信的训练与推理环境。本文通过拓扑与信息论论证严格证明了此类编码的结构不可逆性：即便在理想化攻击者假设下，逆向重构在逻辑上亦不可能；而在实际部署中，攻击者对原始数据的条件熵趋于发散，使得重构概率趋近于零。与先前基于自编码器的ppML方法不同，ICA通过将表征学习与下游监督目标对齐，保持了预测效用的完整性，从而在推理阶段无需梯度裁剪、噪声预算或加密运算即可实现低延迟高性能的机器学习。VEIL架构强制执行严格信任边界，支持可扩展的多区域部署，并天然契合“设计即隐私”的监管框架，为构建从结构上确保安全性、高性能与可靠性的企业级机器学习（即使面对后量子威胁）奠定了新基础。