Leadership hijacking in docker swarm and its consequences

Adi Farshteindiker, Rami Puzis

Research output: Contribution to journalArticlepeer-review


With the advent of microservice-based software architectures, an increasing number of modern cloud environments and enterprises use operating system level virtualization, which is often referred to as container infrastructures. Docker Swarm is one of the most popular container orchestration infrastructures, providing high availability and fault tolerance. Occasionally, discovered container escape vulnerabilities allow adversaries to execute code on the host operating system and operate within the cloud infrastructure. We show that Docker Swarm is currently not secured against misbehaving manager nodes. This allows a high impact, high probability privilege escalation attack, which we refer to as leadership hijacking, the possibility of which is neglected by the current cloud security literature. Cloud lateral movement and defense evasion payloads allow an adversary to leverage the Docker Swarm functionality to control each and every host in the underlying cluster. We demonstrate an end-to-end attack, in which an adversary with access to an application running on the cluster achieves full control of the cluster. To reduce the probability of a successful high impact attack, container orchestration infrastructures must reduce the trust level of participating nodes and, in particular, incorporate adversary immune leader election algorithms.

Original languageAmerican English
Article number914
Issue number7
StatePublished - 1 Jul 2021


  • Cloud
  • Defense evasion
  • Docker Swarm
  • Leader election
  • Privilege escalation

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Mathematical Physics
  • Physics and Astronomy (miscellaneous)
  • Electrical and Electronic Engineering


Dive into the research topics of 'Leadership hijacking in docker swarm and its consequences'. Together they form a unique fingerprint.

Cite this