AI RESEARCH
Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning
arXiv CS.AI
•
ArXi:2603.10692v1 Announce Type: cross While Secure Aggregation (SA) protects update confidentiality in Cross-silo Federated Learning, it fails to guarantee aggregation integrity, allowing malicious servers to silently omit or tamper with updates. Existing verifiable aggregation schemes rely on heavyweight cryptography (e.g., ZKPs, HE), incurring computational costs that scale poorly with model size. In this paper, we propose a lightweight architecture that shifts from extrinsic cryptographic proofs to \textit{Intrinsic Proofs.