Mohammad Naseri (University College London), Jamie Hayes (DeepMind), Emiliano De Cristofaro (University College London & Alan Turing Institute)

Federated Learning (FL) allows multiple participants to train machine learning models collaboratively by keeping their datasets local while only exchanging model updates. Alas, this is not necessarily free from privacy and robustness vulnerabilities, e.g., via membership, property, and backdoor attacks. This paper investigates whether and to what extent one can use differential Privacy (DP) to protect both privacy and robustness in FL. To this end, we present a first-of-its-kind evaluation of Local and Central Differential Privacy (LDP/CDP) techniques in FL, assessing their feasibility and effectiveness.

Our experiments show that both DP variants do defend against backdoor attacks, albeit with varying levels of protection-utility trade-offs, but anyway more effectively than other robustness defenses. DP also mitigates white-box membership inference attacks in FL, and our work is the first to show it empirically. Neither LDP nor CDP, however, defend against property inference. Overall, our work provides a comprehensive, re-usable measurement methodology to quantify the trade-offs between robustness/privacy and utility in differentially private FL.

View More Papers

Clarion: Anonymous Communication from Multiparty Shuffling Protocols

Saba Eskandarian (University of North Carolina at Chapel Hill), Dan Boneh (Stanford University)

Read More

hbACSS: How to Robustly Share Many Secrets

Thomas Yurek (University of Illinois at Urbana-Champaign), Licheng Luo (University of Illinois at Urbana-Champaign), Jaiden Fairoze (University of California, Berkeley), Aniket Kate (Purdue University), Andrew Miller (University of Illinois at Urbana-Champaign)

Read More

NSFuzz: Towards Efficient and State-Aware Network Service Fuzzing

Shisong Qin (Tsinghua University), Fan Hu (State Key Laboratory of Mathematical Engineering and Advanced Computing), Bodong Zhao (Tsinghua University), Tingting Yin (Tsinghua University), Chao Zhang (Tsinghua University)

Read More

Property Inference Attacks Against GANs

Junhao Zhou (Xi'an Jiaotong University), Yufei Chen (Xi'an Jiaotong University), Chao Shen (Xi'an Jiaotong University), Yang Zhang (CISPA Helmholtz Center for Information Security)

Read More