DSperse: A Framework for Targeted Verification in Zero-Knowledge Machine Learning
This addresses the problem of inefficient verification in distributed machine learning for practitioners needing trust minimization, though it is incremental as it builds on existing zero-knowledge paradigms.
The paper tackles the high cost of full-model verification in zero-knowledge machine learning by introducing DSperse, a framework for targeted verification of strategic subcomputations, achieving scalable and flexible trust minimization with empirical results on memory usage and runtime.
DSperse is a modular framework for distributed machine learning inference with strategic cryptographic verification. Operating within the emerging paradigm of distributed zero-knowledge machine learning, DSperse avoids the high cost and rigidity of full-model circuitization by enabling targeted verification of strategically chosen subcomputations. These verifiable segments, or "slices", may cover part or all of the inference pipeline, with global consistency enforced through audit, replication, or economic incentives. This architecture supports a pragmatic form of trust minimization, localizing zero-knowledge proofs to the components where they provide the greatest value. We evaluate DSperse using multiple proving systems and report empirical results on memory usage, runtime, and circuit behavior under sliced and unsliced configurations. By allowing proof boundaries to align flexibly with the model's logical structure, DSperse supports scalable, targeted verification strategies suited to diverse deployment needs.