mlsanityData to 7 Oct 2026

EREBA: Black-box Energy Testing of Adaptive Neural Networks

arXiv 2202.06084 ↗First posted 12 Feb 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 12 Feb 2022.

Builds on

31 of 43 references.

References · 31

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  6. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  7. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  8. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  9. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  10. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  11. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  12. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
19 more
  1. 2016Adaptive Computation Time for Recurrent Neural Networkscited by 479
  2. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  3. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  4. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 307
  5. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  6. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 185
  7. 2017Adaptive Neural Networks for Efficient Inferencecited by 161
  8. 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
  9. 2018DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systemscited by 144
  10. 2018Dynamic Channel Pruning: Feature Boosting and Suppressioncited by 129
  11. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  12. 2017Distributed Deep Neural Networks over the Cloud, the Edge and End Devicescited by 119
  13. 2016Spatially Adaptive Computation Time for Residual Networkscited by 118
  14. 2018Channel Gating Neural Networkscited by 80
  15. 2018DeepMutation: Mutation Testing of Deep Learning Systemscited by 66
  16. 2020A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inferencecited by 61
  17. 2017Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Executioncited by 59
  18. 2017Adaptive Classification for Prediction Under a Budgetcited by 15
  19. 2017Energy-efficient Amortized Inference with Cascaded Deep Classifierscited by 15

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 2.

5 papers.

  1. 2022NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Modelscited by 47
  2. 2023SlothSpeech: Denial-of-service Attack Against Speech Recognition Modelscited by 9
  3. 2023Dynamic Neural Network is All You Need: Understanding the Robustness of Dynamic Mechanisms in Neural Networkscited by 1
  4. 2025Energy Backdoor Attack to Deep Neural Networkscited by 1
  5. 2025Efficiency Robustness of Dynamic Deep Learning Systemscited by 1