mlsanityData to 14 Oct 2026

RobustEdge: Low Power Adversarial Detection for Cloud-Edge Systems

arXiv 2310.06845 ↗First posted 5 Sep 2023cs.CR cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In practical cloud-edge scenarios, where a resource constrained edge performs data acquisition and a cloud system (having sufficient resources) performs inference tasks with a deep neural network (DNN), adversarial robustness is critical for reliability and ubiquitous deployment. Adversarial detection is a prime adversarial defence technique used in prior literature. However, in prior detection works, the detector is attached to the classifier model and both detector and classifier work in tandem to perform adversarial detection that requires a high computational overhead which is not available at the low-power edge. Therefore, prior works can only perform adversarial detection at the cloud and not at the edge. This means that in case of adversarial attacks, the unfavourable adversarial samples must be communicated to the cloud which leads to energy wastage at the edge device. Therefore, a low-power edge-friendly adversarial detection method is required to improve the energy efficiency of the edge and robustness of the cloud-based classifier. To this end, RobustEdge proposes Quantization-enabled Energy Separation (QES) training with "early detection and exit" to perform edge-based low cost adversarial detection. The QES-trained detector implemented at the edge blocks adversarial data transmission to the classifier model, thereby improving adversarial robustness and energy-efficiency of the Cloud-Edge system.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 41 references that are in the map. First posted on arXiv 5 Sep 2023.

Builds on

21 of 41 references.

References · 21

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2016Adversarial examples in the physical worldcited by 1,769
  4. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  6. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  7. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  8. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  9. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  10. 2017Adversarial Attacks on Neural Network Policiescited by 320
  11. 2017On Detecting Adversarial Perturbationscited by 232
  12. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
9 more
  1. 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 125
  2. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  3. 2019When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attackscited by 87
  4. 2019BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Servicescited by 68
  5. 2017Adversarial and Clean Data Are Not Twinscited by 52
  6. 2018Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergycited by 51
  7. 2019GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classificationcited by 20
  8. 2021DetectX -- Adversarial Input Detection using Current Signatures in Memristive XBar Arrayscited by 5
  9. 2021Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networkscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Quantitative Analysis of Deeply Quantized Tiny Neural Networks Robust to Adversarial Attacks
  2. 2024David and Goliath: An Empirical Evaluation of Attacks and Defenses for QNNs at the Deep Edge
  3. 2021A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustness
  4. 2021On the Adversarial Robustness of Quantized Neural Networks
  5. 2025MS2Edge: Towards Energy-Efficient and Crisp Edge Detection with Multi-Scale Residual Learning in SNNs
  6. 2021Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators
  7. 2025Breaking the Limits of Quantization-Aware Defenses: QADT-R for Robustness Against Patch-Based Adversarial Attacks in QNNs
  8. 2023Adversarial Defenses via Vector Quantization