English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Cloud computing paradigms have emerged as a major facility to store andprocess the massive data produced by various business units, publicorganizations, Internet-of-Things, and cyber-physical systems. To meet users'performance requirements while maximizing resource utilization to achievecost-efficiency, cloud administrators leverage schedulers to orchestrate tasksto different physical nodes and allow applications from different users toshare the same physical node. On the other hand, micro-architectural attackscan exploit the shared resources to compromise the confidentiality/integrity ofa co-located victim application. Since co-location is an essential requirementfor micro-architectural attacks, in this work, we investigate whether attackerscan exploit the cloud schedulers to satisfy the co-location requirement. Ouranalysis shows that for cloud schedulers that allow users to submit applicationrequirements, an attacker can carefully select the attacker's applicationrequirements to influence the scheduler to co-locate it with a targeted victimapplication. We call such attack Replication Attack (Repttack). Ourexperimental results, in both a simulated cluster environment and a realcluster, show similar trends; a single attack instance can reach up to 50%co-location rate and with only 5 instances the co-location rate can reach up to80%. Furthermore, we propose and evaluate a mitigation strategy that can helpdefend against Repttack. We believe that our results highlight the fact thatschedulers in multi-user clusters need to be more carefully designed withsecurity in mind, and the process of making scheduling decisions should involveas little user-defined information as possible.

Repttack: Exploiting Cloud Schedulers to Guide Co-Location Attacks