Proof of Compliance for Anonymous, Unlinkable Messages

ePrint Report: Proof of Compliance for Anonymous, Unlinkable Messages

Mingxun Zhou, Elaine Shi, Giulia Fanti

Anonymous systems are susceptible to malicious activity. For instance, in anonymous payment systems, users may engage in illicit practices like money laundering. Similarly, anonymous federated learning systems decouple user updates to a central machine learning model from the user's identity; malicious users can manipulate their updates to poison the model. Today, compliance with system-generated rules in such systems can be guaranteed at the level of …

anonymous compliance eprint report federated federated learning instance laundering machine machine learning malicious may messages money money laundering payment payment systems practices proof report shi systems updates