mlsanityData to 14 Oct 2026

Adversarial Attacks to Latent Representations of Distributed Neural Networks in Split Computing

arXiv 2309.17401 ↗First posted 29 Sep 2023cs.LG cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Distributed deep neural networks (DNNs) have been shown to reduce the computational burden of mobile devices and decrease the end-to-end inference latency in edge computing scenarios. While distributed DNNs have been studied, to the best of our knowledge, the resilience of distributed DNNs to adversarial action remains an open problem. In this paper, we fill the existing research gap by rigorously analyzing the robustness of distributed DNNs against adversarial action. We cast this problem in the context of information theory and rigorously proved that (i) the compressed latent dimension improves the robustness but also affect task-oriented performance; and (ii) the deeper splitting point enhances the robustness but also increases the computational burden. These two trade-offs provide a novel perspective to design robust distributed DNN. To test our theoretical findings, we perform extensive experimental analysis by considering 6 different DNN architectures, 6 different approaches for distributed DNN and 10 different adversarial attacks using the ImageNet-1K dataset.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 53 of its 78 references that are in the map. First posted on arXiv 29 Sep 2023.

Builds on

53 of 78 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2023Segment Anythingcited by 8,234
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  9. 2016Adversarial examples in the physical worldcited by 1,769
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  11. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  12. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
38 more
  1. 2016Deep Variational Information Bottleneckcited by 930
  2. 2018Robustness May Be at Odds with Accuracycited by 880
  3. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  5. 2018MINE: Mutual Information Neural Estimationcited by 683
  6. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  7. 2019On Variational Bounds of Mutual Informationcited by 559
  8. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  9. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 503
  10. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  11. 2019On Evaluating Adversarial Robustnesscited by 447
  12. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 235
  13. 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
  14. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 175
  15. 2018Disentangling Adversarial Robustness and Generalizationcited by 172
  16. 2021A Universal Law of Robustness via Isoperimetrycited by 151
  17. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  18. 2017Over the Air Deep Learning Based Radio Signal Classificationcited by 121
  19. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 120
  20. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 115
  21. 2019BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systemscited by 95
  22. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  23. 2019VC Classes are Adversarially Robustly Learnable, but Only Improperlycited by 83
  24. 2018JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Servicescited by 80
  25. 2018In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learningcited by 80
  26. 2018Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principlecited by 70
  27. 2019BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Servicescited by 68
  28. 2020A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inferencecited by 61
  29. 2021Triangle Attack: A Query-efficient Decision-based Adversarial Attackcited by 48
  30. 2020End-to-end Learning of Compressible Featurescited by 43
  31. 2021Supervised Compression for Resource-Constrained Edge Computing Systemscited by 31
  32. 2022Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneckcited by 30
  33. 2022BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computingcited by 28
  34. 2020Adversarial Machine Learning in Wireless Communications using RF Data: A Reviewcited by 25
  35. 2021Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustnesscited by 20
  36. 2020Pareto-Optimal Bit Allocation for Collaborative Intelligencecited by 17
  37. 2019On Robustness to Adversarial Examples and Polynomial Optimizationcited by 14
  38. 2022Adversarially Robust Learning with Tolerancecited by 9

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126
  2. 2026The Persistent Vulnerability of Aligned AI Systemscited by 0