DualDefense: EnhancingPrivacyandMitigating PoisoningAttacksinFederatedLearning

Feb-16-2026, 05:42:44 GMT–Neural Information Processing Systems

DDFedsimultaneously boosts privacyprotection andmitigatespoisoning attacks, without introducing new participant roles or disrupting the existing FL topology.DDFedinitially leveragescutting-edge fullyhomomorphic encryption (FHE)tosecurely aggregatemodelupdates, without theimpractical requirement for non-colluding two-server setups and ensures strong privacy protection.

artificial intelligence, machine learning, poisoning attack, (16 more...)

Neural Information Processing Systems

Feb-16-2026, 05:42:44 GMT

Conferences PDF

Add feedback

Country:
- Asia > China (0.04)

Genre:
- Research Report > New Finding (0.46)

Industry:
- Information Technology > Security & Privacy (1.00)

Technology:
- Information Technology
  - Artificial Intelligence > Machine Learning (1.00)
  - Security & Privacy (1.00)

Duplicate Docs Excel Report

Title
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning

Similar Docs Excel Report more

Title	Similarity	Source
None found