Federated learning (FL) goes beyond traditional, centralized machine learning by distributing model training among a large collection of edge clients. These clients cooperatively train a global, e.g., cloud-hosted, model without disclosing their local, private training data. The global model is then shared among all the participants which use it for local predictions. This paper proves that FL systems can be turned into covert channels to implement a stealth communication infrastructure. The main intuition is that, during federated training, a malicious sender can poison the global model by submitting purposely crafted examples. Although the effect of the model poisoning is negligible to other participants and does not alter the overall model performance, it can be observed by a malicious receiver and used to transmit a sequence of bits. We mounted our attack on an FL system to verify its feasibility. Experimental evidence shows that this covert channel is reliable, efficient, and extremely hard to counter. These results highlight that our new attacker model threatens FL infrastructures.

Turning Federated Learning Systems into Covert Channels / Gabriele Costa, Fabio Pinelli, Simone Soderi, Gabriele Tolomei. - In: IEEE ACCESS. - ISSN 2169-3536. - 10:(2022), p. 130642. [10.1109/ACCESS.2022.3229124]

Turning Federated Learning Systems into Covert Channels

Gabriele Costa;Fabio Pinelli;Simone Soderi;
2022

Abstract

Federated learning (FL) goes beyond traditional, centralized machine learning by distributing model training among a large collection of edge clients. These clients cooperatively train a global, e.g., cloud-hosted, model without disclosing their local, private training data. The global model is then shared among all the participants which use it for local predictions. This paper proves that FL systems can be turned into covert channels to implement a stealth communication infrastructure. The main intuition is that, during federated training, a malicious sender can poison the global model by submitting purposely crafted examples. Although the effect of the model poisoning is negligible to other participants and does not alter the overall model performance, it can be observed by a malicious receiver and used to transmit a sequence of bits. We mounted our attack on an FL system to verify its feasibility. Experimental evidence shows that this covert channel is reliable, efficient, and extremely hard to counter. These results highlight that our new attacker model threatens FL infrastructures.
2022
10
130642
Gabriele Costa; Fabio Pinelli; Simone Soderi; Gabriele Tolomei
File in questo prodotto:
File Dimensione Formato  
Turning_Federated_Learning_Systems_Into_Covert_Channels.pdf

Accesso chiuso

Licenza: Tutti i diritti riservati
Dimensione 1.12 MB
Formato Adobe PDF
1.12 MB Adobe PDF   Richiedi una copia all'autore

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1499169
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 21
  • ???jsp.display-item.citation.isi??? ND
social impact