Virat Shejwalkar (UMass Amherst), Amir Houmansadr (UMass Amherst)

Federated learning (FL) enables many data owners (e.g., mobile devices) to train a joint ML model (e.g., a next-word prediction classifier) without the need of sharing their private training data.

However, FL is known to be susceptible to poisoning attacks by malicious participants (e.g., adversary-owned mobile devices) who aim at hampering the accuracy of the jointly trained model through sending malicious inputs during the federated training process.

In this paper, we present a generic framework for model poisoning attacks on FL. We show that our framework leads to poisoning attacks that substantially outperform state-of-the-art model poisoning attacks by large margins. For instance, our attacks result in $1.5times$ to $60times$ higher reductions in the accuracy of FL models compared to previously discovered poisoning attacks.

Our work demonstrates that existing Byzantine-robust FL algorithms are significantly more susceptible to model poisoning than previously thought. Motivated by this, we design a defense against FL poisoning, called emph{divide-and-conquer} (DnC). We demonstrate that DnC outperforms all existing Byzantine-robust FL algorithms in defeating model poisoning attacks,
specifically, it is $2.5times$ to $12times$ more resilient in our experiments with different datasets and models.

View More Papers

Is Your Firmware Real or Re-Hosted? A case study...

Abraham A. Clements, Logan Carpenter, William A. Moeglein (Sandia National Laboratories), Christopher Wright (Purdue University)

Read More

Differentially Private Health Tokens for Estimating COVID-19 Risk

David Butler, Chris Hicks, James Bell, Carsten Maple, and Jon Crowcroft (The Alan Turing Institute)

Read More

FlowLens: Enabling Efficient Flow Classification for ML-based Network Security...

Diogo Barradas (INESC-ID, Instituto Superior Técnico, Universidade de Lisboa), Nuno Santos (INESC-ID, Instituto Superior Técnico, Universidade de Lisboa), Luis Rodrigues (INESC-ID, Instituto Superior Técnico, Universidade de Lisboa), Salvatore Signorello (LASIGE, Faculdade de Ciências, Universidade de Lisboa), Fernando M. V. Ramos (INESC-ID, Instituto Superior Técnico, Universidade de Lisboa), André Madeira (INESC-ID, Instituto Superior Técnico, Universidade de…

Read More

WATSON: Abstracting Behaviors from Audit Logs via Aggregation of...

Jun Zeng (National University of Singapore), Zheng Leong Chua (Independent Researcher), Yinfang Chen (National University of Singapore), Kaihang Ji (National University of Singapore), Zhenkai Liang (National University of Singapore), Jian Mao (Beihang University)

Read More