Insecure Until Proven Updated: Analyzing AMD SEV's Remote Attestation

被引:31
作者
Buhren, Robert [1 ]
Werling, Christian [2 ]
Seifert, Jean-Pierre [1 ]
机构
[1] Secur Telecommun, Berlin, Germany
[2] Hasso Plattner Inst, Potsdam, Germany
来源
PROCEEDINGS OF THE 2019 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (CCS'19) | 2019年
关键词
virtualization; Secure Encrypted Virtualization; cloud computing; shielding systems; SEV; remote attestation;
D O I
10.1145/3319535.3354216
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Cloud computing is one of the most prominent technologies to host Internet services that unfortunately leads to an increased risk of data theft. Customers of cloud services have to trust the cloud providers, as they control the building blocks that form the cloud. This includes the hypervisor enabling the sharing of a single hardware platform an-long multiple tenants. Executing in a higher-privileged CPU mode, the hypervisor has direct access to the memory of virtual machines. While data at rest can be protected using well-known disk encryption methods, data residing in main memory is still threatened by a potentially malicious cloud provider. AMD Secure Encrypted Virtualization (SEV) claims a new level of protection in such cloud scenarios. AMD SEV encrypts the main memory of virtual machines with VM-specific keys, thereby denying the higher-privileged hypervisor access to a guest's memory. To enable the cloud customer to verify the correct deployment of his virtual machine, SEV additionally introduces a remote attestation protocol. This protocol is a crucial component of the SEV technology that can prove that SEV protection is place and that the virtual machine was not subject to manipulation. This paper analyzes the firmware components that implement the SEV remote attestation protocol on the current AMD Epyc CPU series. We demonstrate that it is possible to extract critical CPU-specific keys that are fundamental for the security of the remote attestation protocol. Building on the extracted keys, we propose attacks that allow a malicious cloud provider a complete circumvention of the SEV protection mechanisms. Although the underlying firmware issues were already fixed by AMD we show that the can cut series of AMD Epyc CPUs, i.e., the Naples series, does not prevent the installation of previous firmware versions. We show that the severity of our proposed attacks is very high as no purely software-based mitigations are possible. This effectively renders the SEV technology on current AMD Epyc CPUs useless when confronted with an untrusted cloud provider. To overcome these issues, we also propose robust changes to the SEV design that allow future generations of the SEV technology to mitigate the proposed attacks.
引用
收藏
页码:1087 / 1099
页数:13
相关论文
共 35 条
[11]  
Coreboot Project, 2014, COREBOOT PROJECT
[12]  
CTS Labs, 2018, SEV SEC ADV AMD PROC
[13]  
Farkas Uri, 2019, AMDFLAWS TECHNICAL D
[14]   An analysis of security issues for cloud computing [J].
Hashizume, Keiko ;
Rosado, David G. ;
Fernandez-Medina, Eduardo ;
Fernandez, Eduardo B. .
JOURNAL OF INTERNET SERVICES AND APPLICATIONS, 2013, 4 (01) :1-13
[15]  
Hetzelt F, 2017, ACM SIGPLAN NOTICES, V52, P129, DOI [10.1145/3050748.3050763, 10.1145/3140607.3050763]
[16]  
Intel Security Center, 2019, INT CSME SERV PLATF
[17]  
Intel Security Center, 2019, INT FIRMW 2018 4 QSR
[18]  
Jin S, 2011, INT SYMP MICROARCH, P272
[19]  
Kandias M, 2013, LECT NOTES COMPUT SC, V6983, P93
[20]  
Kaplan AMD, 2016, AMD MEMORY ENCRYPTIO