Mingling with the Good to Backdoor Federated Learning

Federated learning (FL) is a decentralized machine learning technique that allows multiple entities to jointly train a model while preserving dataset privacy. However, its distributed nature has raised various security concerns, which have been addressed by increasingly sophisticated defenses. These protections utilize a range of data sources and metrics to, for example, filter out malicious model updates, ensuring that the impact of attacks is minimized or eliminated. This paper explores the feasibility of designing a generic attack method capable of installing backdoors in FL while evading a diverse array of defenses. Specifically, we focus on an attacker strategy called MIGO, which aims to produce model updates that subtly blend with legitimate ones. The resulting effect is a gradual integration of a backdoor into the global model, often ensuring its persistence long after the attack concludes, while generating enough ambiguity to hinder the effectiveness of defenses. MIGO was employed to implant three types of backdoors across five datasets and different model architectures. The results demonstrate the significant threat posed by these backdoors, as MIGO consistently achieved exceptionally high backdoor accuracy (exceeding 90%) while maintaining the utility of the main task. Moreover, MIGO exhibited strong evasion capabilities against ten defenses, including several state-of-the-art methods. When compared to four other attack strategies, MIGO consistently outperformed them across most configurations. Notably, even in extreme scenarios where the attacker controls just 0.1% of the clients, the results indicate that successful backdoor insertion is possible if the attacker can persist for a sufficient number of rounds.

Key Contributions

MIGO attack strategy that produces malicious FL model updates designed to blend with legitimate client updates, generating ambiguity that defeats anomaly-based defenses
Demonstrates backdoor persistence long after the attack concludes, surviving across multiple FL rounds
Shows successful backdoor insertion even with only 0.1% of malicious clients, evaluated across 5 datasets, 3 backdoor types, and 10 defenses

🛡️ Threat Analysis

Model Poisoning

MIGO is explicitly a backdoor insertion attack for federated learning — it implants hidden, trigger-activated targeted behavior into the global model while maintaining normal performance on clean inputs. FL backdoor attacks with trigger-based goals are ML10, not ML02.