Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructure

Federated learning enables industrial operators to train shared intrusion detection models without disclosing proprietary operational telemetry. However, existing defenses operate strictly in update space, leaving aggregators blind to data poisoning; model updates derived from fabricated telemetr...

Verifying Differentially Private Median Estimation

Differential Privacy DP is a robust privacy guarantee that is widely employed in private data analysis today, finding broad application in domains such as statistical query release and machine learning. However, DP achieves privacy by introducing noise into data or query answers, which malicious...

Critical Zcash Bug Could Have Allowed 'Infinite Counterfeit' Cryptocurrency

The developers behind the privacy-minded Zcash cryptocurrency have recently discovered and patched a highly dangerous vulnerability in the most secretive way that could have allowed an attacker to coin an infinite number of Zcash ZEC. Yes, infinite… like a never-ending source of money. Launched i...