17823555. SUPERVISED ANOMALY DETECTION IN FEDERATED LEARNING simplified abstract (International Business Machines Corporation)

From WikiPatents
Jump to navigation Jump to search

SUPERVISED ANOMALY DETECTION IN FEDERATED LEARNING

Organization Name

International Business Machines Corporation

Inventor(s)

Wei-Han Lee of White Plains NY (US)

Pengrui Quan of Los Angeles CA (US)

MUDHAKAR Srivatsa of White Plains NY (US)

Changchang Liu of White Plains NY (US)

SUPERVISED ANOMALY DETECTION IN FEDERATED LEARNING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17823555 titled 'SUPERVISED ANOMALY DETECTION IN FEDERATED LEARNING

Simplified Explanation

The abstract describes a method, program, and system for supervised anomaly detection in federated learning. The server generates a training dataset with malicious and benign data samples, trains models on these samples, generates model updates, and trains an anomaly detector on these updates for detection in the federated learning system.

  • Server generates training dataset with malicious and benign data samples
  • Trains update-generating models on the data samples
  • Generates benign and malicious model updates
  • Trains anomaly detector on the model updates
  • Deploys anomaly detector for supervised anomaly detection in the federated learning system

---

      1. Potential Applications
  • Cybersecurity in federated learning systems
  • Fraud detection in financial transactions
  • Intrusion detection in network security
      1. Problems Solved
  • Detection of malicious activities in federated learning
  • Identification of anomalies in data samples
  • Prevention of security breaches in the system
      1. Benefits
  • Improved security in federated learning environments
  • Early detection of anomalies and malicious behavior
  • Enhanced protection of sensitive data


Original Abstract Submitted

A computer-implemented method, a computer program product, and a computer system for supervised anomaly detection in federated learning. A server in a federated learning system generates a training dataset including malicious data samples and benign data samples. The server trains update-generating models on the malicious data samples and the benign data samples in the training dataset. The server generates benign model updates and malicious model updates, through training the update-generating models. The server trains an anomaly detector on the malicious model updates and the benign model updates. The server deploys the anomaly detector to the federated learning system, for supervised anomaly detection in the federated learning system.

Retrieved from "http://wikipatents.org/index.php?title=17823555._SUPERVISED_ANOMALY_DETECTION_IN_FEDERATED_LEARNING_simplified_abstract_(International_Business_Machines_Corporation)&oldid=37080"