research-article

Open access

EREBA: black-box energy testing of adaptive neural networks

Authors:

Yaswanth Yadlapalli,

Cong LiuAuthors Info & Claims

ICSE '22: Proceedings of the 44th International Conference on Software Engineering

Pages 835 - 846

https://doi.org/10.1145/3510003.3510088

Published: 05 July 2022 Publication History

Abstract

Recently, various Deep Neural Network (DNN) models have been proposed for environments like embedded systems with stringent energy constraints. The fundamental problem of determining the robustness of a DNN with respect to its energy consumption (energy robustness) is relatively unexplored compared to accuracy-based robustness. This work investigates the energy robustness of Adaptive Neural Networks (AdNNs), a type of energy-saving DNNs proposed for many energy-sensitive domains and have recently gained traction. We propose EREBA, the first black-box testing method for determining the energy robustness of an AdNN. EREBA explores and infers the relationship between inputs and the energy consumption of AdNNs to generate energy surging samples. Extensive implementation and evaluation using three state-of-the-art AdNNs demonstrate that test inputs generated by EREBA could degrade the performance of the system substantially. The test inputs generated by EREBA can increase the energy consumption of AdNNs by 2,000% compared to the original inputs. Our results also show that test inputs generated via EREBA are valuable in detecting energy surging inputs.

References

[1]

Jacob Benesty, Jingdong Chen, Yiteng Huang, and Israel Cohen. 2009. Pearson Correlation Coefficient. In Noise Reduction in Speech Processing. Springer, 37--40.

Digital Library

[2]

Tolga Bolukbasi, Joseph Wang, Ofer Dekel, and Venkatesh Saligrama. 2017. Adaptive Neural Networks for Efficient Inference. In Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 527--536.

Digital Library

[3]

Andrew P. Bradley. 1997. The Use of the Area under the ROC Curve in the Evaluation of Machine Learning Algorithms. Pattern Recogn. 30, 7 (July 1997), 1145--1159.

Digital Library

[4]

Nicholas Carlini and David Wagner. 2017. Towards Evaluating the Robustness of Neural Networks. In 2017 IEEE Symposium on Security and Privacy (SP). IEEE, 39--57.

[5]

Shuyu Cheng, Yinpeng Dong, Tianyu Pang, Hang Su, and Jun Zhu. 2019. Improving Black-box Adversarial Attacks with a Transfer-based Prior. In Advances in Neural Information Processing Systems. 10932--10942.

[6]

Corinna Cortes and Vladimir Vapnik. 1995. Support-vector Networks. Machine learning 20, 3 (1995), 273--297.

Digital Library

[7]

Michael Figurnov, Maxwell D Collins, Yukun Zhu, Li Zhang, Jonathan Huang, Dmitry Vetrov, and Ruslan Salakhutdinov. 2017. Spatially Adaptive Computation Time for Residual Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1039--1048.

[8]

Xitong Gao, Yiren Zhao, Łukasz Dudziak, Robert Mullins, and Cheng-zhong Xu. 2018. Dynamic Channel Pruning: Feature Boosting and Suppression. arXiv preprint arXiv:1810.05331 (2018).

[9]

Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, and Wieland Brendel. 2018. ImageNet-trained CNNs Are Biased Towards Texture; Increasing Shape Bias Improves Accuracy and Robustness. arXiv preprint arXiv:1811.12231 (2018).

[10]

Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and Harnessing Adversarial Examples. arXiv preprint arXiv:1412.6572 (2014).

[11]

Alex Graves. 2016. Adaptive Computation time for Recurrent Neural Networks. arXiv preprint arXiv:1603.08983 (2016).

[12]

Jiaqi Guan, Yang Liu, Qiang Liu, and Jian Peng. 2017. Energy-efficient Amortized Inference with Cascaded Deep Classifiers. arXiv preprint arXiv:1710.03368 (2017).

[13]

Mirazul Haque, Anki Chauhan, Cong Liu, and Wei Yang. 2020. ILFO: Adversarial Attack on Adaptive Neural Networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14264--14273.

[14]

Dan Hendrycks and Thomas Dietterich. 2019. Benchmarking Neural Network Robustness to Common Corruptions and Perturbations. Proceedings of the International Conference on Learning Representations (2019).

[15]

Sanghyun Hong, Yiğitcan Kaya, Ionuţ-Vlad Modoranu, and Tudor Dumitraş. 2020. A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference. arXiv preprint arXiv:2010.02432 (2020).

[16]

Weizhe Hua, Yuan Zhou, Christopher M De Sa, Zhiru Zhang, and G Edward Suh. 2019. Channel Gating Neural Networks. In Advances in Neural Information Processing Systems. 1884--1894.

[17]

Andrew Ilyas, Logan Engstrom, Anish Athalye, and Jessy Lin. 2018. Blackbox Adversarial Attacks with Limited Queries and Information. arXiv preprint arXiv:1804.08598 (2018).

[18]

Sven Köhler, Benedict Herzog, Timo Hönig, Lukas Wenzel, Max Plauth, Jörg Nolte, Andreas Polze, and Wolfgang Schröder-Preikschat. 2020. Pinpoint the Joules: Unifying Runtime-Support for Energy Measurements on Heterogeneous Systems. In 2020 IEEE/ACM International Workshop on Runtime and Operating Systems for Supercomputers (ROSS). IEEE, 31--40.

[19]

Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. (2009).

[20]

Lanlan Liu and Jia Deng. 2018. Dynamic Deep Neural Networks: Optimizing Accuracy-efficiency Trade-offs by Selective Execution. In Thirty-Second AAAI Conference on Artificial Intelligence.

[21]

Yanpei Liu, Xinyun Chen, Chang Liu, and Dawn Song. 2016. Delving into Transferable Adversarial Examples and Black-box Attacks. arXiv preprint arXiv:1611.02770 (2016).

[22]

Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, et al. 2018. Deepgauge: Multi-granularity Testing Criteria for Deep Learning Systems. In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering. 120--131.

Digital Library

[23]

Lei Ma, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Felix Juefei-Xu, Chao Xie, Li Li, Yang Liu, Jianjun Zhao, et al. 2018. Deepmutation: Mutation Testing of Deep Learning Systems. In 2018 IEEE 29th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 100--111.

[24]

Feng Nan and Venkatesh Saligrama. 2017. Adaptive Classification for Prediction Under a Budget. In Advances in Neural Information Processing Systems. 4727--4737.

[25]

Nvidia. 2017. Nvidia TX2 User Manual.

[26]

Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, David Sculley, Sebastian Nowozin, Joshua Dillon, Balaji Lakshminarayanan, and Jasper Snoek. 2019. Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift. In Advances in Neural Information Processing Systems. 13991--14002.

[27]

Nicolas Papernot, Patrick McDaniel, and Ian Goodfellow. 2016. Transferability in Machine Learning: from Phenomena to Black-box Attacks using Adversarial Samples. arXiv preprint arXiv:1605.07277 (2016).

[28]

Nicolas Papernot, Patrick McDaniel, Ian Goodfellow, Somesh Jha, Z Berkay Celik, and Ananthram Swami. 2017. Practical Black-box Attacks against Machine Learning. In Proceedings of the 2017 ACM on Asia conference on computer and communications security. 506--519.

Digital Library

[29]

Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z Berkay Celik, and Ananthram Swami. 2016. The Limitations of Deep Learning in Adversarial Settings. In 2016 IEEE European Symposium on Security and Privacy (EuroS&P). IEEE, 372--387.

[30]

Kexin Pei, Yinzhi Cao, Junfeng Yang, and Suman Jana. 2017. Deepxplore: Automated Whitebox Testing of Deep Learning Systems. In proceedings of the 26th Symposium on Operating Systems Principles. 1--18.

Digital Library

[31]

Joaquin Quionero-Candela, Masashi Sugiyama, Anton Schwaighofer, and Neil D Lawrence. 2009. Dataset shift in machine learning. The MIT Press.

[32]

Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing Properties of Neural Networks. arXiv preprint arXiv:1312.6199 (2013).

[33]

Surat Teerapittayanon, Bradley McDanel, and Hsiang-Tsung Kung. 2016. Branchynet: Fast Inference via Early Exiting from Deep Neural Networks. In 2016 23rd International Conference on Pattern Recognition (ICPR). IEEE, 2464--2469.

[34]

Surat Teerapittayanon, Bradley McDanel, and Hsiang-Tsung Kung. 2017. Distributed Deep Neural Networks over the Cloud, the Edge and End Devices. In 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS). IEEE, 328--339.

[35]

Tensorflow. 2009. Tensorflow Deep Learning Framework. https://www.tensorflow.org/datasets/catalog/cifar10.

[36]

Tensorflow. 2009. Tensorflow Deep Learning Framework. https://www.tensorflow.org/datasets/catalog/cifar100.

[37]

Yuchi Tian, Kexin Pei, Suman Jana, and Baishakhi Ray. 2018. Deeptest: Automated Testing of Deep-neural-network-driven Autonomous Cars. In Proceedings of the 40th international conference on software engineering. 303--314.

Digital Library

[38]

Xin Wang, Fisher Yu, Zi-Yi Dou, Trevor Darrell, and Joseph E Gonzalez. 2018. Skipnet: Learning Dynamic Routing in Convolutional Networks. In Proceedings of the European Conference on Computer Vision (ECCV). 409--424.

Digital Library

[39]

Wikipedia. [n.d.]. Peak Signal-to-Noise Ratio. https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio.

[40]

Wikipedia. [n.d.]. Structural Similarity Index Measure. https://en.wikipedia.org/wiki/Structural_similarity.

[41]

Zuxuan Wu, Tushar Nagarajan, Abhishek Kumar, Steven Rennie, Larry S Davis, Kristen Grauman, and Rogerio Feris. 2018. Blockdrop: Dynamic Inference Paths in Residual Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8817--8826.

[42]

Qizhe Xie, Minh-Thang Luong, Eduard Hovy, and Quoc V Le. 2020. Self-training with Noisy Student Improves Imagenet Classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10687--10698.

[43]

Xiaofei Xie, Lei Ma, Felix Juefei-Xu, Minhui Xue, Hongxu Chen, Yang Liu, Jianjun Zhao, Bo Li, Jianxiong Yin, and Simon See. 2019. DeepHunter: a Coverage-guided Fuzz Testing Framework for Deep Neural Networks. In Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis. 146--157.

Digital Library

[44]

Le Yang, Yizeng Han, Xi Chen, Shiji Song, Jifeng Dai, and Gao Huang. 2020. Resolution Adaptive Networks for Efficient Inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2366--2375.

Cited By

Shi JYang ZKang HXu BHe JLo DRoychoudhury PPaiva AAbreu RStorey MSharif BXia X(2024)Greening Large Language Models of CodeProceedings of the 46th International Conference on Software Engineering: Software Engineering in Society10.1145/3639475.3640097(142-153)Online publication date: 14-Apr-2024
https://dl.acm.org/doi/10.1145/3639475.3640097
Varma KNumanoğlu AKaya YDumitraş T(2024)Understanding, Uncovering, and Mitigating the Causes of Inference Slowdown for Language Models2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)10.1109/SaTML59370.2024.00042(723-740)Online publication date: 9-Apr-2024
https://doi.org/10.1109/SaTML59370.2024.00042
Haque MChen SHaque WLiu CYang W(2023)AntiNODE: Evaluating Efficiency Robustness of Neural ODEs2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)10.1109/ICCVW60793.2023.00164(1499-1509)Online publication date: 2-Oct-2023
https://doi.org/10.1109/ICCVW60793.2023.00164
Show More Cited By

Index Terms

EREBA: black-box energy testing of adaptive neural networks
1. Security and privacy
  1. Software and application security

Recommendations

Precise Energy Consumption Measurements of Heterogeneous Artificial Intelligence Workloads
High Performance Computing. ISC High Performance 2022 International Workshops
Abstract
With the rise of artificial intelligence (AI) in recent years and the subsequent increase in complexity of the applied models, the growing demand in computational resources is starting to pose a significant challenge. The need for higher compute ...
Energy Consumption Analysis of Batch Runs of Evolutionary Algorithms
GECCO '24 Companion: Proceedings of the Genetic and Evolutionary Computation Conference Companion

We analyze the energy consumption of running evolutionary algorithms in batch as a function of the rest time between runs. It is shown that energy consumption can be reduced by 5%-8% by inserting short pauses between runs to reduce hysteretic phenomena.
Plant classification in the wild: Energy evaluation for deep learning models
Abstract
Having a system that can take an image of a natural scene and accurately classify the plants in it is of undeniable importance. However, the complexities of dealing with natural scene images and the vast diversity of plants in the wild make ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

ICSE '22: Proceedings of the 44th International Conference on Software Engineering

May 2022

2508 pages

ISBN:9781450392211

DOI:10.1145/3510003

General Chair:
Matthew B Dwyer
University of Virginia
,
Program Chairs:
Daniela Damian
University of Victoria, Canada
,
Andreas Zeller
CISPA, Germany

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGSOFT: ACM Special Interest Group on Software Engineering

In-Cooperation

IEEE CS

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 July 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

NSF
Siemens Fellowship

Conference

ICSE '22

Sponsor:

SIGSOFT

ICSE '22: 44th International Conference on Software Engineering

May 21 - 29, 2022

Pennsylvania, Pittsburgh

Acceptance Rates

Overall Acceptance Rate 276 of 1,856 submissions, 15%

Upcoming Conference

ICSE 2025

2025 IEEE/ACM 46th International Conference on Software Engineering

April 26 - May 3, 2025

Ottawa , ON , Canada

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
272
Total Downloads

Downloads (Last 12 months)142
Downloads (Last 6 weeks)18

Reflects downloads up to 26 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Shi JYang ZKang HXu BHe JLo DRoychoudhury PPaiva AAbreu RStorey MSharif BXia X(2024)Greening Large Language Models of CodeProceedings of the 46th International Conference on Software Engineering: Software Engineering in Society10.1145/3639475.3640097(142-153)Online publication date: 14-Apr-2024
https://dl.acm.org/doi/10.1145/3639475.3640097
Varma KNumanoğlu AKaya YDumitraş T(2024)Understanding, Uncovering, and Mitigating the Causes of Inference Slowdown for Language Models2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)10.1109/SaTML59370.2024.00042(723-740)Online publication date: 9-Apr-2024
https://doi.org/10.1109/SaTML59370.2024.00042
Haque MChen SHaque WLiu CYang W(2023)AntiNODE: Evaluating Efficiency Robustness of Neural ODEs2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)10.1109/ICCVW60793.2023.00164(1499-1509)Online publication date: 2-Oct-2023
https://doi.org/10.1109/ICCVW60793.2023.00164
Haque MYang W(2023)Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networks2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)10.1109/ICCVW60793.2023.00163(1489-1498)Online publication date: 2-Oct-2023
https://doi.org/10.1109/ICCVW60793.2023.00163
Chen SSong ZHaque MLiu CYang W(2022)NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR52688.2022.01493(15344-15353)Online publication date: Jun-2022
https://doi.org/10.1109/CVPR52688.2022.01493

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents