PPFPL: Cross-Silo Privacy-Preserving Federated Prototype Learning Against Data Poisoning Attacks

Summary

This research article proposes PPFPL, a privacy-preserving federated prototype learning framework for cross-silo federated learning. It uses prototypes as client-submitted model updates to limit the effect of poisoned Non-IID data, and a secure aggregation protocol built on homomorphic encryption that runs on two servers to achieve Byzantine-robust aggregation. The authors report theoretical convergence and privacy analyses and experiments on public datasets showing resistance to data poisoning under Non-IID settings.

Topics

• Adversarial machine learning

Related items

• MediumFake AI Attacks Spread Across US Companies: How MSSPs Can Stop Incidents EarlySimilar attack · The Hacker News
• MediumRansomware extortion gets personal as attackers target employees’ familiesSimilar attack · CSO Online
• MediumLangflow's Critical Authenticated RCE Flaw Targeted in 1,423 Honeypot Exploit AttemptsSimilar attack · The Hacker News
• MediumAnthropic 'SneakPeek' Flaw Is a Silent Zero-Click ThreatSimilar attack · Dark Reading
• HighCVE-2026-104103: Ludwig archive extraction allows writes outside extraction directorySimilar attack · NVD/CVE Database