CoChat
Sign Up
Cited by 320Security and Verification in ComputingCryptographic Implementations and SecurityCryptography and Data Security

Leaky Cauldron on the Dark Land: Understanding Memory Side-Channel Hazards in SGX

Open access
Wang, Wenhao, Chen, Guoxing, Pan, Xiaorui, Zhang, Yinqian, Wang, XiaoFeng, Bindschaedler, Vincent, Tang, Haixu, Gunter, Carl A.·2017·Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security
DOI 10.1145/3133956.3134038PMC PMC6405214
Open this paper in CoChat — free account

Abstract

Side-channel risks of Intel's SGX have recently attracted great attention. Under the spotlight is the newly discovered page-fault attack, in which an OS-level adversary induces page faults to observe the page-level access patterns of a protected process running in an SGX enclave. With almost all proposed defense focusing on this attack, little is known about whether such efforts indeed raises the bar for the adversary, whether a simple variation of the attack renders all protection ineffective, not to mention an in-depth understanding of other attack surfaces in the SGX system. In the paper, we report the first step toward systematic analyses of side-channel threats that SGX faces, focusing on the risks associated with its memory management. Our research identifies 8 potential attack vectors, ranging from TLB to DRAM modules. More importantly, we highlight the common misunderstandings about SGX memory side channels, demonstrating that high frequent AEXs can be avoided when recovering EdDSA secret key through a new page channel and fine-grained monitoring of enclave programs (at the level of 64B) can be done through combining both cache and cross-enclave DRAM channels. Our findings reveal the gap between the ongoing security research on SGX and its side-channel weaknesses, redefine the side-channel threat model for secure enclaves, and can provoke a discussion on when to use such a system and how to use it securely.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3133956.3134038

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • TEEs are inherently hardware-dependent and may be vulnerable to microarchitectural attacks.

    “TEE are inherently hardware-dependent and may be vulnerable to microarchitectural attacks [38], [39], [40], [41], [42], [43].”

    From Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference (2026) · cites this paper as [43]

    The Introduction describes SGX as a CPU-based TEE whose use of shared resources can expose it to side-channel attacks. The Attack Vectors section identifies hardware caches that create such channels. The paper supports the vulnerability claim for SGX, but does not establish that all TEEs are inherently hardware-dependent. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 32

  1. [9]Aciiçmez Onur, Brumley Billy Bob, and Grabher Philipp. New results on instruction cache attacks. In 12th international conference on Cryptographic hardware and embedded systems, 2010.
  2. [10]Anati Ittai, Gueron Shay, Johnson Simon, and Scarlata Vincent. Innovative technology for cpu based attestation and sealing. In Proceedings of the 2nd international workshop on hardware and architectural support for security and privacy, volume 13, 2013.
  3. [12]Benger Naomi, Pol Joop van de, Smart Nigel P., and Yarom Yuval. “Ooh Aah… Just a Little Bit”: A small amount of side channel can go a long way. In 16th International Workshop on Cryptographic Hardware and Embedded Systems, 2014.
  4. [13]Daniel J Bernstein Niels Duif, Lange Tanja, Schwabe Peter, and Yang Bo-Yin. High-speed high-security signatures. Journal of Cryptographic Engineering, pages 1– 13, 2012.
  5. [14]Chen Sanchuan, Zhang Xiaokuan, Reiter Michael, and Zhang Yinqian. Detecting privileged side-channel attacks in shielded execution with DÉJÀ VU. In 12th ACM Symposium on Information, Computer and Communications Security, 2017.
  6. [15]Costan Victor, Lebedev Ilia, and Devadas Srinivas. Sanctum: Minimal hardware extensions for strong software isolation. In 25th USENIX Security Symposium USENIX Association, 2016.
  7. [16]Gruss Daniel, Spreitzer Raphael, and Mangard Stefan. Cache template attacks: Automating attacks on inclusive last-level caches. In 24th USENIX Security Symposium, 2015.
  8. [17]Gullasch D, Bangerter E, and Krenn S Cache games – bringing access-based cache attacks on AES to practice. In 32nd IEEE Symposium on Security and Privacy, 2011.
  9. [18]Hund Ralf, Willems Carsten, and Holz Thorsten. Practical timing side channel attacks against kernel space ASLR. In 34th IEEE Symposium on Security and Privacy, 2013.
  10. [20]Irazoqui Gorka, Eisenbarth Thomas, and Sunar Berk. S$A: A shared cache attack that works across cores and defies VM sandboxing—and its application to AES. In IEEE Symposium on Security and Privacy, 2015.
  11. [21]Irazoqui Gorka, Eisenbarth Thomas, and Sunar Berk. Systematic reverse engineering of cache slice selection in intel processors. In Digital System Design (DSD), 2015 Euromicro Conference on, pages 629– 636. IEEE, 2015.
  12. [22]Irazoqui Gorka, Inci Mehmet Sinan, Eisenbarth Thomas,, and Sunar Berk. Wait a minute! a fast, cross-vm attack on AES. In 17th International Symposium Research in Attacks, Intrusions and Defenses, 2014.
  13. [23]Kayaalp Mehmet, Nael Abu-Ghazaleh Dmitry Ponomarev, and Jaleel Aamer. A high-resolution side-channel attack on last-level cache. In 53rd Annual Design Automation Conference, 2016.
  14. [24]Lampson Butler W.. A note on the confinement problem. Commun. ACM, 16(10), 10 1973.
  15. [25]Lee Sangho, Shih Ming-Wei, Gera Prasun, Kim Taesoo, Kim Hyesoon, and Peinado Marcus. Inferring fine-grained control flow inside SGX enclaves with branch shadowing. CoRR, abs/1611.06952, 2016. · arXiv
  16. [26]Lipp Moritz, Gruss Daniel, Spreitzer Raphael, Maurice Clémentine, and Mangard Stefan. Armageddon: Cache attacks on mobile devices. In USENIX Security Symposium, 2016.
  17. [27]Liu Fangfei, Yarom Yuval, Ge Qian, Heiser Gernot, and Lee Ruby B. Last-level cache side-channel attacks are practical. In IEEE Symposium on Security and Privacy, 2015.
  18. [28]Neve Michael and Seifert Jean-Pierre. Advances on access-driven cache attacks on AES. In 13th international conference on selected areas in cryptography, 2007.
  19. [29]Oren Yossef, Kemerlis Vasileios P., Sethumadhavan Simha, and Keromytis Angelos D. The spy in the sandbox: Practical cache attacks in javascript and their implications. In 22nd ACM SIGSAC Conference on Computer and Communications Security, 2015.
  20. [30]Osvik Dag Arne, Shamir Adi, and Tromer Eran. Cache attacks and countermeasures: the case of AES. In 6th Cryptographers’ track at the RSA conference on Topics in Cryptology, 2006.
  21. [32]Pessl Peter, Gruss Daniel, Maurice Clementine, Schwarz Michael, and Mangard Stefan. Drama: Exploiting dram addressing for cross-cpu attacks. In Proceedings of the 25th USENIX Security Symposium, 2016.
  22. [33]Seo Jaebaek, Lee Byoungyoung, Kim Sungmin, Shih Ming-Wei, Shin Insik, Han Dongsu, and Kim Taesoo. SGX-Shield: Enabling Address Space Layout Randomization for SGX Programs (to appear). In Proceedings of the 2017 Annual Network and Distributed System Security Symposium (NDSS), San Diego, CA, 2 2017.
  23. [34]Shih Ming-Wei, Lee Sangho, Kim Taesoo, and Peinado Marcus. T-SGX: Eradicating Controlled-Channel Attacks Against Enclave Programs (to appear). In Proceedings of the 2017 Annual Network and Distributed System Security Symposium (NDSS), San Diego, CA, 2 2017.
  24. [35]Shinde Shweta, Zheng Leong Chua Viswesh Narayanan, and Saxena Prateek. Preventing page faults from telling your secrets. In 11th ACM Symposium on Information, Computer and Communications Security, 2016.
  25. [36]Tromer Eran, Osvik Dag Arne, and Shamir Adi. Efficient cache attacks on AES, and countermeasures. Journal of Cryptology, 23(2): 37– 71, 1 2010.
  26. [37]Tsai Chia-Che, Kumar Saurabh Arora Nehal Bandi, Jain Bhushan, Jannen William, John Jitin, Harry A Kalodner Vrushali Kulkarni, Oliveira Daniela, and Porter Donald E. Cooperation and security isolation of library oses for multi-process applications. In Proceedings of the Ninth European Conference on Computer Systems, page 9 ACM, 2014.
  27. [38]Xiao Yuan, Zhang Xiaokuan, Zhang Yinqian, and Teodorescu Radu. One bit flips, one cloud flops: Cross-vm row hammer attacks and privilege escalation. In USENIX Security Symposium, 2016.
  28. [39]Xu Yuanzhong, Cui Weidong, and Peinado Marcus. Controlled-channel attacks: Deterministic side channels for untrusted operating systems. In 36th IEEE Symposium on Security and Privacy, 2015.
  29. [41]Yarom Yuval and Falkner Katrina. Flush+reload: A high resolution, low noise, L3 cache side-channel attack. In USENIX Security Symposium, 2014.
  30. [42]Zhang Xiaokuan, Xiao Yuan, and Zhang Yinqian. Return-oriented flush-reload side channels on arm and their implications for android devices. In ACM Conference on Computer and Communications Security, 2016.
  31. [43]Zhang Yinqian, Juels Ari, Reiter Michael K., and Ristenpart Thomas. Cross-VM side channels and their use to extract private keys. In ACM Conference on Computer and Communications Security, 2012.
  32. [44]Zhang Yinqian, Juels Ari, Reiter Michael K., and Ristenpart Thomas. Cross-tenant side-channel attacks in PaaS clouds. In ACM Conference on Computer and Communications Security, 2014.

Cited by

Sorted by citations

Authors
Wang, W., Chen, G., Pan, X., Zhang, Y., Wang, X., Bindschaedler, V., Tang, H., & Gunter, C. A.
Affiliations
  • Chinese Academy of Sciences (CN)
  • The Ohio State University (US)
  • Indiana University Bloomington (US)
  • University of Illinois Urbana-Champaign (US)
ORCID
Venue
Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security
Publisher
ACM
Published
2017-10-30
Volume
2017
Pages
2421-2434
ISSN
1543-7221 (ISSN-L)
DOI
10.1145/3133956.3134038
PMC
PMC6405214
OpenAlex
W2616901112
Cited by
320
References
1
Citations by year
2026: 11 · 2025: 30 · 2024: 37 · 2023: 22 · 2022: 27 · 2021: 48 · 2020: 61 · 2019: 53 · 2018: 28 · 2017: 3
FWCI
18.09
Type
conference paper
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
  • ACM SIGSAC Conference on Computer and Communications Security (CCS) (publishedVersion)
  • PubMed (publishedVersion)
  • Europe PMC (PubMed Central) (acceptedVersion)
  • PubMed Central (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Natural Science Foundation of China (61379139)
  • National Institutes of Health (1R01HG007078)
  • Division of Computer and Network Systems (12-23967, 13-30491, 14-08944)
  • National Science Foundation (1408874, 1527141, 1566444, 1618493)
  • Army Research Office (W911NF1610127)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Security and Verification in Computing
  • Physical Sciences › Computer Science › Artificial Intelligence › Cryptographic Implementations and Security
  • Physical Sciences › Computer Science › Artificial Intelligence › Cryptography and Data Security
Keywords
Intel SGX, side-channel attacks, cache side-channel, attack vectors

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review