Exploiting a Thermal Side Channel for Power Attacks in Multi-Tenant Data Centers

The power capacity of multi-tenant data centers is typically oversubscribed in order to increase the utilization of expensive power infrastructure. This practice can create dangerous situations and compromise data center availability if the designed power capacity is exceeded. This paper demonstrates that current safeguards are vulnerable to well-timed power attacks launched by malicious tenants (i.e., attackers). Further, we demonstrate that there is a physical side channel --- a thermal side channel due to hot air recirculation --- that contains information about the benign tenants' runtime power usage and can enable a malicious tenant to time power attacks effectively. In particular, we design a state-augmented Kalman filter to extract this information from the side channel and guide an attacker to use its maximum power at moments that coincide with the benign tenants' high power demand, thus overloading the shared power capacity. Our experimental results show that an attacker can capture 54% of all attack opportunities, significantly compromising the data center availability. Finally, we discuss a set of possible defense strategies to safeguard the data center infrastructure against power attacks.

[1]  Sandeep K. S. Gupta,et al.  A transient model for data center thermal prediction , 2012, 2012 International Green Computing Conference (IGCC).

[2]  Ethan Katz-Bassett,et al.  CSPAN: cost-effective geo-replicated storage spanning multiple cloud services , 2013, SIGCOMM.

[3]  Xiaorui Wang,et al.  Power Attack: An Increasing Threat to Data Centers , 2014, NDSS.

[4]  Dimitrios Pendarakis,et al.  ContainerLeaks: Emerging Security Threats of Information Leakages in Container Clouds , 2017, 2017 47th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN).

[5]  Wei Xu,et al.  Increasing large-scale data center capacity by statistical power control , 2016, EuroSys.

[6]  Vyas Sekar,et al.  Nomad: Mitigating Arbitrary Cloud Side Channels via Provider-Assisted Migration , 2015, CCS.

[7]  Adam Wierman,et al.  A market approach for handling power emergencies in multi-tenant data center , 2016, 2016 IEEE International Symposium on High Performance Computer Architecture (HPCA).

[8]  Mordechai Guri,et al.  BitWhisper: Covert Signaling Channel between Air-Gapped Computers Using Thermal Manipulations , 2015, 2015 IEEE 28th Computer Security Foundations Symposium.

[9]  Cullen E. Bash,et al.  Kratos: Automated Management of Cooling Capacity in Data Centers With Adaptive Vent Tiles , 2009 .

[10]  Peter Reiher,et al.  A taxonomy of DDoS attack and DDoS defense mechanisms , 2004, CCRV.

[11]  Ethan Katz-Bassett,et al.  SPANStore: cost-effective geo-replicated storage spanning multiple cloud services , 2013, SOSP.

[12]  Siva Sai Yerubandi,et al.  Differential Power Analysis , 2002 .

[13]  Song Guo,et al.  Can We Beat DDoS Attacks in Clouds? , 2014, IEEE Transactions on Parallel and Distributed Systems.

[14]  Ruby B. Lee,et al.  Physical attack protection with human-secure virtualization in data centers , 2012, IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN 2012).

[15]  Minyi Guo,et al.  Power Attack Defense: Securing Battery-Backed Data Centers , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

[16]  Jeffrey S. Chase,et al.  Making Scheduling "Cool": Temperature-Aware Workload Placement in Data Centers , 2005, USENIX Annual Technical Conference, General Track.

[17]  Luiz André Barroso,et al.  The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines , 2009, The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines.

[18]  Wolf-Dietrich Weber,et al.  Power provisioning for a warehouse-sized computer , 2007, ISCA '07.

[19]  Anand Sivasubramaniam,et al.  Aggressive Datacenter Power Provisioning with Batteries , 2013, TOCS.

[20]  Li Li,et al.  Coordinating Liquid and Free Air Cooling with Workload Allocation for Data Center Power Minimization , 2014, ICAC.

[21]  Adam Wierman,et al.  Greening Multi-Tenant Data Center Demand Response , 2015, PERV.

[22]  Dan Tsafrir,et al.  Experience with using the Parallel Workloads Archive , 2014, J. Parallel Distributed Comput..

[23]  S. Patankar Airflow and Cooling in a Data Center , 2010 .

[24]  Bin Li,et al.  Dynamo: Facebook's Data Center-Wide Power Management System , 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

[25]  P. Kocher,et al.  Di erential Power Analysis , 1999 .

[26]  Albert G. Greenberg,et al.  The cost of a cloud: research problems in data center networks , 2008, CCRV.

[27]  Sandeep K. S. Gupta,et al.  Energy-Efficient Thermal-Aware Task Scheduling for Homogeneous High-Performance Computing Data Centers: A Cyber-Physical Approach , 2008, IEEE Transactions on Parallel and Distributed Systems.

[28]  S. Haykin Kalman Filtering and Neural Networks , 2001 .

[29]  Shaolei Ren,et al.  Paying to save: Reducing cost of colocation data center via rewards , 2015, 2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA).

[30]  Chao Li,et al.  A quantitative analysis of cooling power in container-based data centers , 2011, 2011 IEEE International Symposium on Workload Characterization (IISWC).

[31]  John H. Seader,et al.  Tier Classifications Define Site Infrastructure Performance , 2006 .

[32]  Nanning Zheng,et al.  HEB: Deploying and managing hybrid energy buffers for improving datacenter efficiency and economy , 2015, 2015 ACM/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA).

[33]  Michael K. Reiter,et al.  Cross-VM side channels and their use to extract private keys , 2012, CCS.

[34]  Paramvir Bahl,et al.  Low Latency Geo-distributed Data Analytics , 2015, SIGCOMM.

[35]  D. Birchall,et al.  Computational Fluid Dynamics , 2020, Radial Flow Turbocompressors.

[36]  Anand Sivasubramaniam,et al.  Virtualizing power distribution in datacenters , 2013, ISCA.