Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Dishonest Approximate Computing: A Coming Crisis for Cloud Clients (2405.15322v1)

Published 24 May 2024 in cs.CR and cs.AR

Abstract: Approximate Computing (AC) has emerged as a promising technique for achieving energy-efficient architectures and is expected to become an effective technique for reducing the electricity cost for cloud service providers (CSP). However, the potential misuse of AC has not received adequate attention, which is a coming crisis behind the blueprint of AC. Driven by the pursuit of illegal financial profits, untrusted CSPs may deploy low-cost AC devices and deceive clients by presenting AC services as promised accurate computing products, while falsely claiming AC outputs as accurate results. This misuse of AC will cause both financial loss and computing degradation to cloud clients. In this paper, we define this malicious attack as DisHonest Approximate Computing (DHAC) and analyze the technical challenges faced by clients in detecting such attacks. To address this issue, we propose two golden model free detection methods: Residual Class Check (RCC) and Forward-Backward Check (FBC). RCC provides clients a low-cost approach to infer the residual class to which a legitimate accurate output should belong. By comparing the residual class of the returned result, clients can determine whether a computing service contains any AC elements. FBC detects potential DHAC by computing an invertible check branch using the intermediate values of the program. It compares the values before entering and after returning from the check branch to identify any discrepancies. Both RCC and FBC can be executed concurrently with real computing tasks, enabling real-time DHAC detection with current inputs. Our experimental results show that both RCC and FBC can detect over 96%-99% of DHAC cases without misjudging any legitimate accurate results.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. Q. A. Ahmed, M. Awais, and M. Platzner, “Maas: Hiding trojans in approximate circuits,” in 2023 24th International Symposium on Quality Electronic Design (ISQED).   IEEE, 2023, pp. 1–6.
  2. G. Armeniakos, G. Zervakis, D. Soudris, and J. Henkel, “Hardware approximate techniques for deep neural network accelerators: A survey,” ACM Computing Surveys, vol. 55, no. 4, pp. 1–36, 2022.
  3. E. Azarkhish, D. Rossi, I. Loi, and L. Benini, “Neurostream: Scalable and energy efficient deep learning with smart memory cubes,” IEEE Transactions on Parallel and Distributed Systems, vol. 29, no. 2, pp. 420–434, 2017.
  4. H. B. Barua and K. C. Mondal, “Approximate computing: A survey of recent trends—bringing greenness to computing and communication,” Journal of The Institution of Engineers (India): Series B, vol. 100, no. 6, pp. 619–626, 2019.
  5. V. Camus, J. Schlachter, and C. Enz, “A low-power carry cut-back approximate adder with fixed-point implementation and floating-point precision,” in Proceedings of the 53rd Annual Design Automation Conference, 2016, pp. 1–6.
  6. Y.-H. Chen, T.-J. Yang, J. Emer, and V. Sze, “Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices,” IEEE Journal on Emerging and Selected Topics in Circuits and Systems, vol. 9, no. 2, pp. 292–308, 2019.
  7. R. Houlihan, X. Du, C. C. Tan, J. Wu, and M. Guizani, “Auditing cloud service level agreement on vm cpu speed,” in 2014 IEEE International Conference on Communications (ICC).   IEEE, 2014, pp. 799–803.
  8. https://ehw.fit.vutbr.cz/evoapproxlib/.
  9. M. Imani, A. Sokolova, R. Garcia, A. Huang, F. Wu, B. Aksanli, and T. Rosing, “Approxlp: Approximate multiplication with linearization and iterative error control,” in Proceedings of the 56th Annual Design Automation Conference 2019, 2019, pp. 1–6.
  10. H. Jiang, F. J. H. Santiago, H. Mo, L. Liu, and J. Han, “Approximate arithmetic circuits: A survey, characterization, and recent applications,” Proceedings of the IEEE, vol. 108, no. 12, pp. 2108–2135, 2020.
  11. C.-H. Lin and C. Lin, “High accuracy approximate multiplier with error correction,” in 2013 IEEE 31st international conference on computer design (ICCD).   IEEE, 2013, pp. 33–38.
  12. W. Liu, C. Gu, G. Qu, and M. O’Neill, “Approximate computing and its application to hardware security,” Cyber-Physical Systems Security, pp. 43–67, 2018.
  13. J. N. Mitchell, “Computer multiplication and division using binary logarithms,” IRE Transactions on Electronic Computers, no. 4, pp. 512–517, 1962.
  14. S. Mittal, “A survey of techniques for approximate computing,” ACM Computing Surveys (CSUR), vol. 48, no. 4, pp. 1–33, 2016.
  15. V. Mrazek, R. Hrbacek, Z. Vasicek, and L. Sekanina, “Evoapprox8b: Library of approximate adders and multipliers for circuit design and benchmarking of approximation methods,” in Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017.   IEEE, 2017, pp. 258–261.
  16. V. Mrazek, Z. Vasicek, L. Sekanina, H. Jiang, and J. Han, “Scalable construction of approximate multipliers with formally guaranteed worst case error,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 26, no. 11, pp. 2572–2576, 2018.
  17. A. Rahmati, M. Hicks, D. E. Holcomb, and K. Fu, “Probable cause: The deanonymizing effects of approximate dram,” in Proceedings of the 42nd annual international symposium on computer architecture, 2015, pp. 604–615.
  18. M. Rapp, H. Amrouch, Y. Lin, B. Yu, D. Z. Pan, M. Wolf, and J. Henkel, “Mlcad: A survey of research in machine learning for cad keynote paper,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 41, no. 10, pp. 3162–3181, 2021.
  19. F. Regazzoni, C. Alippi, and I. Polian, “Security: The dark side of approximate computing?” in 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).   IEEE, 2018, pp. 1–6.
  20. M. Shafique, W. Ahmad, R. Hafiz, and J. Henkel, “A low latency generic accuracy configurable adder,” in Proceedings of the 52nd Annual Design Automation Conference, 2015, pp. 1–6.
  21. H. Sharma, J. Park, N. Suda, L. Lai, B. Chau, J. K. Kim, V. Chandra, and H. Esmaeilzadeh, “Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network,” in 2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA).   IEEE, 2018, pp. 764–775.
  22. Y. Wang, J. Dong, Q. Xu, Z. Lu, and G. Qu, “Is it approximate computing or malicious computing?” in Proceedings of the 2020 on Great Lakes Symposium on VLSI, 2020, pp. 333–338.
  23. L. Ye, H. Zhang, J. Shi, and X. Du, “Verifying cloud service level agreement,” in 2012 IEEE Global Communications Conference (GLOBECOM).   IEEE, 2012, pp. 777–782.
  24. P. Yellu, N. Boskov, M. A. Kinsy, and Q. Yu, “Security threats in approximate computing systems,” in Proceedings of the 2019 on Great Lakes Symposium on VLSI, 2019, pp. 387–392.
  25. P. Yellu, N. Chennagouni, and Q. Yu, “Inead: Intermediate node evaluation-based attack detection for secure approximate computing systems,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023.
  26. P. Yellu, M. R. Monjur, T. Kammerer, D. Xu, and Q. Yu, “Security threats and countermeasures for approximate arithmetic computing,” in 2020 25th Asia and South Pacific design automation conference (ASP-DAC).   IEEE, 2020, pp. 259–264.
  27. P. Yellu and Q. Yu, “Securing approximate computing systems via obfuscating approximate-precise boundary,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 42, no. 1, pp. 27–40, 2022.
  28. G. Zervakis, K. Tsoumanis, S. Xydis, D. Soudris, and K. Pekmestzi, “Design-efficient approximate multiplication circuits through partial product perforation,” IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 24, no. 10, pp. 3105–3117, 2016.
  29. H. Zhang, L. Ye, J. Shi, X. Du, and M. Guizani, “Verifying cloud service-level agreement by a third-party auditor,” Security and Communication Networks, vol. 7, no. 3, pp. 492–502, 2014.
  30. N. Zhu, W. L. Goh, G. Wang, and K. S. Yeo, “Enhanced low-power high-speed adder for error-tolerant application,” in 2010 International SoC Design Conference.   IEEE, 2010, pp. 323–327.
  31. N. Zhu, W. L. Goh, W. Zhang, K. S. Yeo, and Z. H. Kong, “Design of low-power high-speed truncation-error-tolerant adder and its application in digital signal processing,” IEEE transactions on very large scale integration (VLSI) systems, vol. 18, no. 8, pp. 1225–1229, 2009.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets