mlsanityData to 14 Oct 2026

Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning

arXiv 2305.03888 ↗First posted 6 May 2023cs.CR cs.AI cs.ARcited by 10

Not on the map. Why?

Abstract (arXiv)

In recent years, on-device deep learning has gained attention as a means of developing affordable deep learning applications for mobile devices. However, on-device models are constrained by limited energy and computation resources. In the mean time, a poisoning attack known as sponge poisoning has been developed.This attack involves feeding the model with poisoned examples to increase the energy consumption during inference. As previous work is focusing on server hardware accelerators, in this work, we extend the sponge poisoning attack to an on-device scenario to evaluate the vulnerability of mobile device processors. We present an on-device sponge poisoning attack pipeline to simulate the streaming and consistent inference scenario to bridge the knowledge gap in the on-device setting. Our exclusive experimental analysis with processors and on-device networks shows that sponge poisoning attacks can effectively pollute the modern processor with its built-in accelerator. We analyze the impact of different factors in the sponge poisoning algorithm and highlight the need for improved defense mechanisms to prevent such attacks on on-device deep learning applications.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 35 of its 70 references that are in the map. First posted on arXiv 6 May 2023.

Builds on

35 of 70 references.

References · 35

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  8. 2019Searching for MobileNetV3cited by 1,994
  9. 2016Adversarial examples in the physical worldcited by 1,769
  10. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  11. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  12. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 618
23 more
  1. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 603
  2. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  3. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  4. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  5. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  6. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
  7. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 165
  8. 2017SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networkscited by 135
  9. 2018Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbationcited by 134
  10. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 111
  11. 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 77
  12. 2020Poisoning Attacks on Algorithmic Fairnesscited by 59
  13. 2020Natural Language Processing Advancements By Deep Learning: A Surveycited by 50
  14. 2020Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsitycited by 34
  15. 2023Training-free Lexical Backdoor Attacks on Language Modelscited by 31
  16. 2022Energy-Latency Attacks via Sponge Poisoningcited by 29
  17. 2018Data Poisoning Attacks against Online Learningcited by 27
  18. 2022Machine Learning Security against Data Poisoning: Are We There Yet?cited by 23
  19. 2018Efficient Sparse-Winograd Convolutional Neural Networkscited by 20
  20. 2021Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Appscited by 19
  21. 2021On Robustness of Neural Semantic Parserscited by 14
  22. 2022Smart App Attack: Hacking Deep Learning Models in Android Appscited by 12
  23. 2019Automatic Generation of Multi-precision Multi-arithmetic CNN Accelerators for FPGAscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 4.

10 papers.

  1. 2025LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loopscited by 9
  2. 2025Energy-Latency Attacks: A New Adversarial Threat to Deep Learningcited by 5
  3. 2024The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networkscited by 3
  4. 2025Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruningcited by 2
  5. 2026Resource Consumption Threats in Large Language Modelscited by 2
  6. 2025Energy Backdoor Attack to Deep Neural Networkscited by 1
  7. 2024Evaluating Model Robustness Using Adaptive Sparse L0 Regularizationcited by 0
  8. 2026VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Modelscited by 0
  9. 2026SoK: Colluding Adversaries in Machine Learning Pipelinescited by 0
  10. 2026SoK: Attack and Defense Landscape of Mobile On-device AI Systemscited by 0