DeSMP: Differential Privacy-exploited Stealthy Model Poisoning Attacks in Federated Learning

TL;DR

This paper introduces DeSMP, a novel stealthy model poisoning attack in federated learning that exploits differential privacy noise, and proposes an RL-based defense to counter it, highlighting vulnerabilities despite privacy measures.

Contribution

The paper presents the first differential privacy-exploited stealthy poisoning attack in federated learning and a dynamic RL-based defense mechanism to mitigate such threats.

Findings

DeSMP effectively poisons FL models while remaining stealthy.

RL-based defense dynamically adjusts privacy levels to detect and prevent attacks.

Empirical results show the attack's success on classification and regression tasks.

Abstract

Federated learning (FL) has become an emerging machine learning technique lately due to its efficacy in safeguarding the client's confidential information. Nevertheless, despite the inherent and additional privacy-preserving mechanisms (e.g., differential privacy, secure multi-party computation, etc.), the FL models are still vulnerable to various privacy-violating and security-compromising attacks (e.g., data or model poisoning) due to their numerous attack vectors which in turn, make the models either ineffective or sub-optimal. Existing adversarial models focusing on untargeted model poisoning attacks are not enough stealthy and persistent at the same time because of their conflicting nature (large scale attacks are easier to detect and vice versa) and thus, remain an unsolved research problem in this adversarial learning paradigm. Considering this, in this paper, we analyze this adversarial learning process in an FL setting and show that a stealthy and persistent model poisoning attack can be conducted exploiting the differential noise. More specifically, we develop an unprecedented DP-exploited stealthy model poisoning (DeSMP) attack for FL models. Our empirical analysis on both the classification and regression tasks using two popular datasets reflects the effectiveness of the proposed DeSMP attack. Moreover, we develop a novel reinforcement learning (RL)-based defense strategy against such model poisoning attacks which can intelligently and dynamically select the privacy level of the FL models to minimize the DeSMP attack surface and facilitate the attack detection.