RMPocalypse: How a Catch-22 Breaks AMD SEV-SNP
Benedict Schlüter, Shweta Shinde
摘要
AMD SEV-SNP offers confidential computing in form of confidential VMs, such that the untrusted hypervisor cannot tamper with its confidentiality and integrity. SEV-SNP, the latest addition, ensures integrity via the Reverse Map Table (RMP) that stops the hypervisor from tampering guest page mappings. AMD uses RMP entries to protect the rest of the RMP, thus causing a Catch-22 during the RMP setup phase. To address this, SEV-SNP relies on AMD's Platform Security Processor (PSP), that resides next to the x86 cores executing SEV-SNP VMs, to perform the RMP initialization. During initialization, only PSP should be able to alter the RMP memory. All other memory accesses must be fenced, especially from the x86 cores. We present RMPocalypse, a novel attack that shows a critical gap in the security of RMP initialization, wherein the x86 cores maliciously control parts of the initial RMP state. Our analysis shows that the vulnerability arises due to the complex, but insufficient, interplay of multiple hardware components and distributed access controls. To show the impact of our finding, we exploit this gap to break confidentiality and integrity guarantees of SEV-SNP. We demonstrate RMPocalypse by enabling debug on production-mode CVMs, faking attestation, VMSA state replay, and code injection.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- BreakFAST: Confused Deputy Attack on Infinity Fabric to Break AMD SEV-SNPPhilipp Giersfeld, Benedict Schlüter, Shweta ShindeS&P 2026 · 被引用 1 次
- STALEUS: Breaking AMD SEV-SNP via Memory IncoherenceBenedict Schlüter, Shweta ShindeUSENIX Security 2026
- DDRop: Active Memory Interposer Attacks on Confidential VMs by Dropping DDR5 WritesJesse De Meulemeester, Stefan Gloor, Patrick Jattke, Daniel Moghimi 等CCS 2026
- FABRICKED: Misconfiguring Infinity Fabric to Break AMD SEV-SNPBenedict Schlüter, Christoph Wech, Shweta ShindeUSENIX Security 2026
- HarborMaster: Rollback Detection for Trusted Distributed ComputingShubham Mishra, Alexander Thomas, Nurzhan Abdrassilov, Kaiyuan Chen 等VLDB 2026
它引用的顶会 Paper14
- CIPHERLEAKS: Breaking Constant-time Cryptography on AMD SEV via the Ciphertext Side ChannelMengyuan Li, Yinqian Zhang, Huibo Wang, Kang Li 等USENIX Security 2021 · 被引用 130 次
- A Systematic Look at Ciphertext Side Channels on AMD SEV-SNPMengyuan Li, Luca Wilke, Jan Wichelmann, Thomas Eisenbarth 等S&P 2022 · 被引用 87 次
- SEVurity: No Security Without Integrity : Breaking Integrity-Free Memory Encryption with Minimal AssumptionsLuca Wilke, Jan Wichelmann, Mathias Morbitzer, Thomas EisenbarthS&P 2020 · 被引用 72 次
- HECKLER: Breaking Confidential VMs with Malicious InterruptsBenedict Schlüter, Supraja Sridhara, Mark Kuhne, Andrin Bertschi 等USENIX Security 2024 · 被引用 48 次
- WeSee: Using Malicious #VC Interrupts to Break AMD SEV-SNPBenedict Schlüter, Supraja Sridhara, Andrin Bertschi, Shweta ShindeS&P 2024 · 被引用 42 次
相关 Paper
- Heracles: Chosen Plaintext Attack on AMD SEV-SNPBenedict Schlüter, Christoph Wech, Shweta ShindeCCS 2025 · 被引用 1 次
- CounterSEVeillance: Performance-Counter Attacks on AMD SEV-SNPStefan Gast, Hannes Weissteiner, Robin Leander Schröder, Daniel GrussNDSS 2025
- CrossLine: Breaking "Security-by-Crash" based Memory Isolation in AMD SEVMengyuan Li, Yinqian Zhang, Zhiqiang LinCCS 2021 · 被引用 41 次
- One Glitch to Rule Them All: Fault Injection Attacks Against AMD's Secure Encrypted VirtualizationRobert Buhren, Hans Niklas Jacob, Thilo Krachenfels, Jean-Pierre SeifertCCS 2021
- StackWarp: Breaking AMD SEV-SNP Integrity via Deterministic Stack-Pointer Manipulation through the CPU's Stack EngineRuiyi Zhang, Tristan Hornetz, Daniel Weber, Fabian Thomas 等USENIX Security 2026 · 被引用 1 次
