Multi-party Poisoning through Generalized p-Tampering

By Saeed Mahloujifar, Mohammad Mahmoody, Ameer Mohammed. 2018

13 citations recorded by the source corpus.

Subfields: Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Privacy & Security

1. Chris J. M. Yoon
2. Clement Fung
3. Ivan Beschastnikh
4. Muhammad Shayan
5. Dusist Niyato
6. Zehui Xiong
7. Jiawen Kang

Citations in the corpus

• The Limitations of Federated Learning in Sybil Settings (2020, background): “For example, adversaries posing as honest clients can send erroneous updates to poison the trained model [3,8,15,19,23,28,36], invert or reconstruct the data of honest clients [26,41,42,48,54,56], or gain access to models without usefully contributing [34].”
• Biscotti: A Blockchain System for Private and Secure Federated Learning (2021, background): “exploit the private P2P setting to stealthily execute poisoning attacks [12], [18], [46], [47], [48].”